TOP ACTIVATIONS
MAX = 5.857

they had a lot in common . They liked the same
they had one thing in common : a love of bright
. It is a very common bird . It likes to
you may find something in common . This can make even
they had many things in common . They started to have
, one step at a time . Once
They have many things in common . They like the same
They have a lot in common . They become friends .
He searched for a long time but he couldn 't find
up one step at a time , and slowly , the
had lots of things in common , like his love for
, one step at a time . Their mom
the books one at a time . In each book she
had lots of things in common , like his love for
, one number at a time . As he
, one step at a time . They looked at the
, one step at a time . When
One slow step at a time , she followed her mom
wood . One day a trou l be came to the
She searched for a long time until she found something incredible

MIN ACTIVATIONS
MIN = -5.368

day , while Benny was m unch ing on a carrot
They did not know sun fl owers could talk .
She did not know sun fl owers were alive . She
but he didn â t know which way to
restless and couldn â t get to sleep .
realised he wasn â t scared to go to
, Mike and his m itten were insepar able . They
, Molly and her m ule were the best of friends
They want to make snow fl akes for the window .
was their son â s special place . <|endoftext|>
to send soft white snow fl akes into the sky .
bear and didn â t want to go anywhere
and they played make - bel ieve . Finally , they
excited and couldn â t wait to have fun
. Jake had never had por ridge before and he was
and Jack didn â t give up . They
. They never planted sun fl owers again . <|endoftext|> L
onwards , Molly and her m ule were the best of
pen and didn â t know where it was
wealthy prince and his sun fl owers lived happily ever after

INTERVAL 3.051 - 5.857
CONTAINS 0.066%

was smarter . In the end , he said a word
they all had a great time playing games and eating cake
Then give it to someone you like . They will be
. It says , " Join the Jazz Club ! Learn
!" He jumped into the cool water and started playing ,

INTERVAL 0.245 - 3.051
CONTAINS 37.795%

loved to wear all the time . One day , Lily
to show me ?" The butterfly said , " Follow me
He picked up his fork and took a small bite of
girl found the tough magnet . " Hello ," she said
. They hope the mosquito does not come back . <|endoftext|>

INTERVAL -2.562 - 0.245
CONTAINS 61.757%

sauce was better . They both felt angry and sad .
problem , just be careful and take it easy !"
their k ites and their dolls . They had fun in
." <|endoftext|> L ily did not like school . She thought
to pack your backpack for school tomorrow ," her mom said

INTERVAL -5.368 - -2.562
CONTAINS 0.382%

He said , " My shadow is different because I have
for Emma and her little brother Tom . Tom grabbed the
, hopefully you â ll see a purple sunset
took his friend â s advice . He stayed
He knew that all his hard work , practice and creativity
Token they
Token ID484
Feature activation-9.80e-01

Pos logit contributions
oved+0.036
zed+0.035
opes+0.034
ths+0.031
iously+0.031
Neg logit contributions
ulu-0.054
J-0.053
ory-0.052
 Jill-0.050
 common-0.050
Token had
Token ID550
Feature activation-3.50e-01

Pos logit contributions
oved+0.033
zed+0.032
opes+0.032
ths+0.029
sed+0.029
Neg logit contributions
ulu-0.033
J-0.031
ory-0.031
 common-0.029
 Jill-0.029
Token a
Token ID257
Feature activation-6.12e-02

Pos logit contributions
oved+0.012
zed+0.012
opes+0.011
sed+0.011
ths+0.011
Neg logit contributions
ulu-0.011
ory-0.011
J-0.011
ola-0.010
ora-0.010
Token lot
Token ID1256
Feature activation+1.16e+00

Pos logit contributions
sed+0.002
 ow+0.002
opes+0.002
zed+0.002
oved+0.002
Neg logit contributions
ulu-0.002
J-0.002
ill-0.002
ola-0.002
 Jill-0.002
Token in
Token ID287
Feature activation+3.40e-01

Pos logit contributions
ory+0.049
ulu+0.048
J+0.047
emo+0.045
Col+0.045
Neg logit contributions
oved-0.028
 about-0.025
der-0.021
chair-0.021
zed-0.019
Token common
Token ID2219
Feature activation+5.39e+00

Pos logit contributions
ory+0.013
ulu+0.012
ackers+0.011
va+0.011
J+0.010
Neg logit contributions
zed-0.009
oved-0.009
opes-0.008
 ow-0.008
 meanings-0.008
Token.
Token ID13
Feature activation+1.48e-01

Pos logit contributions
ulu+0.173
ory+0.164
J+0.160
 Jill+0.145
ola+0.143
Neg logit contributions
oved-0.199
opes-0.192
zed-0.183
iously-0.174
 meanings-0.169
Token They
Token ID1119
Feature activation-7.08e-02

Pos logit contributions
ory+0.006
ulu+0.006
guard+0.005
ora+0.005
J+0.005
Neg logit contributions
oved-0.004
opes-0.003
sed-0.003
der-0.003
 Leave-0.003
Token liked
Token ID8288
Feature activation+8.12e-01

Pos logit contributions
oved+0.002
zed+0.002
opes+0.002
sed+0.002
ths+0.002
Neg logit contributions
ulu-0.003
ory-0.002
J-0.002
 common-0.002
ola-0.002
Token the
Token ID262
Feature activation-3.49e-01

Pos logit contributions
ulu+0.028
ory+0.027
J+0.027
ola+0.025
 common+0.024
Neg logit contributions
opes-0.025
oved-0.025
zed-0.025
ths-0.024
sed-0.023
Token same
Token ID976
Feature activation+9.26e-01

Pos logit contributions
opes+0.010
oved+0.010
sed+0.010
 ow+0.010
 meanings+0.009
Neg logit contributions
ulu-0.011
J-0.011
 opener-0.010
ola-0.010
ory-0.010
Token they
Token ID484
Feature activation-9.91e-01

Pos logit contributions
oved+0.020
zed+0.020
opes+0.020
ths+0.019
iously+0.019
Neg logit contributions
ory-0.016
J-0.016
ulu-0.016
 common-0.014
ola-0.014
Token had
Token ID550
Feature activation-1.14e-01

Pos logit contributions
oved+0.032
zed+0.030
opes+0.030
ths+0.028
iously+0.028
Neg logit contributions
ulu-0.035
J-0.034
ory-0.034
 common-0.032
 Jill-0.031
Token one
Token ID530
Feature activation+2.28e-01

Pos logit contributions
oved+0.004
zed+0.004
opes+0.004
ths+0.004
iously+0.004
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 Jill-0.003
 common-0.003
Token thing
Token ID1517
Feature activation-8.06e-01

Pos logit contributions
ulu+0.007
ory+0.006
J+0.006
 common+0.006
 Jill+0.006
Neg logit contributions
oved-0.008
zed-0.008
opes-0.008
ths-0.008
iously-0.008
Token in
Token ID287
Feature activation+1.26e+00

Pos logit contributions
oved+0.026
zed+0.025
opes+0.024
ths+0.023
iously+0.023
Neg logit contributions
ulu-0.028
J-0.027
ory-0.027
 Jill-0.025
 common-0.025
Token common
Token ID2219
Feature activation+5.36e+00

Pos logit contributions
ory+0.040
ulu+0.037
J+0.035
ola+0.032
ackers+0.031
Neg logit contributions
zed-0.043
oved-0.043
opes-0.041
 meanings-0.038
iously-0.038
Token:
Token ID25
Feature activation+5.90e-01

Pos logit contributions
ulu+0.158
J+0.152
ory+0.152
 common+0.136
 Jill+0.136
Neg logit contributions
oved-0.205
opes-0.197
zed-0.195
iously-0.184
ths-0.181
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
ulu+0.020
ory+0.020
J+0.019
 common+0.017
ola+0.017
Neg logit contributions
oved-0.019
opes-0.019
zed-0.019
ths-0.017
iously-0.017
Token love
Token ID1842
Feature activation+2.37e+00

Pos logit contributions
ulu+0.040
J+0.040
ory+0.039
ola+0.036
ora+0.034
Neg logit contributions
oved-0.038
sed-0.038
opes-0.037
zed-0.037
 ow-0.036
Token of
Token ID286
Feature activation+4.17e-01

Pos logit contributions
ulu+0.077
J+0.076
ory+0.074
 common+0.066
ola+0.064
Neg logit contributions
oved-0.084
zed-0.079
opes-0.078
iously-0.073
ths-0.072
Token bright
Token ID6016
Feature activation+8.33e-01

Pos logit contributions
ulu+0.013
J+0.013
ory+0.012
 common+0.011
 Jill+0.011
Neg logit contributions
oved-0.015
zed-0.015
opes-0.015
ths-0.014
iously-0.014
Token.
Token ID13
Feature activation+5.53e-01

Pos logit contributions
oved+0.052
zed+0.049
opes+0.049
iously+0.046
ths+0.045
Neg logit contributions
ulu-0.041
J-0.041
ory-0.040
 common-0.036
 Jill-0.036
Token It
Token ID632
Feature activation+9.07e-01

Pos logit contributions
J+0.024
ory+0.024
ulu+0.024
 common+0.021
ackers+0.021
Neg logit contributions
oved-0.012
opes-0.011
 Leave-0.011
sed-0.011
der-0.010
Token is
Token ID318
Feature activation+1.03e+00

Pos logit contributions
ulu+0.030
J+0.030
ory+0.030
 Jill+0.027
 common+0.027
Neg logit contributions
oved-0.031
zed-0.029
opes-0.029
ths-0.027
iously-0.027
Token a
Token ID257
Feature activation-1.07e-01

Pos logit contributions
J+0.038
ory+0.037
ulu+0.036
ola+0.033
ora+0.033
Neg logit contributions
oved-0.031
opes-0.031
sed-0.030
zed-0.029
 ow-0.028
Token very
Token ID845
Feature activation+1.05e+00

Pos logit contributions
sed+0.003
oved+0.003
 ow+0.003
opes+0.003
zed+0.003
Neg logit contributions
J-0.004
ulu-0.003
ory-0.003
ola-0.003
 Jill-0.003
Token common
Token ID2219
Feature activation+5.24e+00

Pos logit contributions
J+0.039
ulu+0.037
ill+0.037
ory+0.036
ola+0.035
Neg logit contributions
sed-0.028
oved-0.028
zed-0.026
 meanings-0.025
 ow-0.024
Token bird
Token ID6512
Feature activation+2.96e-01

Pos logit contributions
J+0.158
ulu+0.158
ory+0.156
ola+0.135
 Jill+0.133
Neg logit contributions
oved-0.190
opes-0.180
sed-0.171
zed-0.168
 meanings-0.164
Token.
Token ID13
Feature activation+6.06e-01

Pos logit contributions
J+0.009
ulu+0.009
ory+0.009
 Jill+0.008
 common+0.008
Neg logit contributions
oved-0.011
zed-0.010
opes-0.010
iously-0.010
sed-0.010
Token It
Token ID632
Feature activation+1.07e+00

Pos logit contributions
ory+0.027
J+0.027
ulu+0.027
 common+0.024
ola+0.023
Neg logit contributions
oved-0.013
opes-0.012
 Leave-0.012
sed-0.012
zed-0.011
Token likes
Token ID7832
Feature activation+1.57e+00

Pos logit contributions
ulu+0.035
J+0.034
ory+0.034
 Jill+0.031
 common+0.031
Neg logit contributions
oved-0.037
zed-0.036
opes-0.036
ths-0.033
iously-0.033
Token to
Token ID284
Feature activation+5.63e-01

Pos logit contributions
ulu+0.053
J+0.051
ory+0.051
 common+0.047
 Jill+0.047
Neg logit contributions
oved-0.053
zed-0.051
opes-0.050
ths-0.047
iously-0.047
Token you
Token ID345
Feature activation+1.37e+00

Pos logit contributions
oved+0.023
zed+0.022
opes+0.022
ths+0.021
iously+0.021
Neg logit contributions
ulu-0.015
J-0.015
ory-0.015
 Jill-0.013
 common-0.013
Token may
Token ID743
Feature activation+7.48e-01

Pos logit contributions
ulu+0.036
ory+0.035
J+0.033
 common+0.032
 Jill+0.031
Neg logit contributions
oved-0.056
zed-0.054
opes-0.054
ths-0.051
iously-0.051
Token find
Token ID1064
Feature activation+1.39e-01

Pos logit contributions
J+0.024
ulu+0.023
ory+0.023
 Jill+0.021
ola+0.020
Neg logit contributions
oved-0.026
zed-0.026
opes-0.025
ths-0.023
iously-0.023
Token something
Token ID1223
Feature activation+6.03e-01

Pos logit contributions
ulu+0.004
J+0.004
ory+0.004
 common+0.003
 Jill+0.003
Neg logit contributions
oved-0.006
zed-0.005
opes-0.005
ths-0.005
iously-0.005
Token in
Token ID287
Feature activation+4.37e-01

Pos logit contributions
ulu+0.018
J+0.017
ory+0.017
 common+0.016
 Jill+0.016
Neg logit contributions
oved-0.023
zed-0.022
opes-0.022
ths-0.021
iously-0.020
Token common
Token ID2219
Feature activation+5.21e+00

Pos logit contributions
ulu+0.014
ory+0.014
J+0.014
ola+0.012
ora+0.012
Neg logit contributions
oved-0.015
zed-0.014
opes-0.014
ths-0.013
 meanings-0.013
Token.
Token ID13
Feature activation-6.58e-01

Pos logit contributions
ulu+0.152
J+0.148
ory+0.146
 Jill+0.132
 common+0.131
Neg logit contributions
oved-0.199
zed-0.191
opes-0.191
iously-0.178
ths-0.178
Token This
Token ID770
Feature activation+4.08e-02

Pos logit contributions
oved+0.020
zed+0.019
opes+0.018
 Leave+0.017
ths+0.017
Neg logit contributions
ulu-0.024
ory-0.024
J-0.023
 common-0.022
 mer-0.021
Token can
Token ID460
Feature activation+1.05e+00

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 common+0.001
 Jill+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token make
Token ID787
Feature activation-2.46e-01

Pos logit contributions
ulu+0.029
J+0.028
ory+0.027
 common+0.025
 Jill+0.025
Neg logit contributions
oved-0.042
zed-0.040
opes-0.040
ths-0.038
iously-0.038
Token even
Token ID772
Feature activation+1.08e+00

Pos logit contributions
oved+0.010
zed+0.009
opes+0.009
ths+0.009
iously+0.009
Neg logit contributions
ulu-0.007
ory-0.007
J-0.007
 common-0.006
 Jill-0.006
Token they
Token ID484
Feature activation-6.91e-01

Pos logit contributions
ory+0.032
ulu+0.031
J+0.029
ora+0.026
 common+0.026
Neg logit contributions
oved-0.041
zed-0.041
opes-0.039
ths-0.038
sed-0.037
Token had
Token ID550
Feature activation-3.62e-01

Pos logit contributions
oved+0.023
zed+0.022
opes+0.022
ths+0.021
iously+0.020
Neg logit contributions
ulu-0.023
J-0.022
ory-0.022
 common-0.021
 Jill-0.020
Token many
Token ID867
Feature activation-2.66e-01

Pos logit contributions
oved+0.013
zed+0.013
opes+0.013
ths+0.012
iously+0.012
Neg logit contributions
ulu-0.011
J-0.011
ory-0.011
 common-0.010
 Jill-0.010
Token things
Token ID1243
Feature activation-1.65e-01

Pos logit contributions
oved+0.010
opes+0.009
zed+0.009
ths+0.008
iously+0.008
Neg logit contributions
ulu-0.008
J-0.008
ory-0.008
 Jill-0.007
 common-0.007
Token in
Token ID287
Feature activation+4.40e-01

Pos logit contributions
oved+0.005
zed+0.005
opes+0.005
ths+0.005
iously+0.005
Neg logit contributions
ulu-0.006
J-0.006
ory-0.006
 common-0.005
 Jill-0.005
Token common
Token ID2219
Feature activation+5.18e+00

Pos logit contributions
ory+0.010
ulu+0.009
J+0.008
ola+0.007
ackers+0.007
Neg logit contributions
oved-0.018
zed-0.018
opes-0.017
 meanings-0.017
 about-0.016
Token.
Token ID13
Feature activation+2.33e-01

Pos logit contributions
ulu+0.156
J+0.149
ory+0.148
 Jill+0.133
 common+0.130
Neg logit contributions
oved-0.197
opes-0.190
zed-0.186
iously-0.175
ths-0.171
Token They
Token ID1119
Feature activation+2.57e-02

Pos logit contributions
ory+0.009
ulu+0.009
J+0.008
 mer+0.008
 shell+0.008
Neg logit contributions
oved-0.006
 Leave-0.006
opes-0.006
 meanings-0.005
 Eventually-0.005
Token started
Token ID2067
Feature activation+2.88e-01

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 common+0.001
 Jill+0.001
Neg logit contributions
oved-0.001
opes-0.001
zed-0.001
sed-0.001
ths-0.001
Token to
Token ID284
Feature activation-4.50e-01

Pos logit contributions
ulu+0.011
J+0.011
ory+0.011
 common+0.010
 Jill+0.010
Neg logit contributions
oved-0.008
zed-0.008
opes-0.008
ths-0.007
iously-0.007
Token have
Token ID423
Feature activation+6.24e-01

Pos logit contributions
oved+0.014
zed+0.014
opes+0.013
 meanings+0.013
ze+0.013
Neg logit contributions
ulu-0.015
ory-0.015
J-0.015
ola-0.013
emo-0.012
Token,
Token ID11
Feature activation-1.43e-01

Pos logit contributions
oved+0.008
zed+0.008
opes+0.008
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.006
J-0.006
ory-0.006
 common-0.005
 Jill-0.005
Token one
Token ID530
Feature activation+1.74e+00

Pos logit contributions
oved+0.005
zed+0.005
opes+0.005
ths+0.005
iously+0.005
Neg logit contributions
ulu-0.004
J-0.004
ory-0.004
 Jill-0.004
 common-0.004
Token step
Token ID2239
Feature activation-1.15e+00

Pos logit contributions
ulu+0.044
J+0.041
ory+0.040
 Jill+0.039
 common+0.036
Neg logit contributions
opes-0.075
oved-0.073
zed-0.072
iously-0.068
ths-0.066
Token at
Token ID379
Feature activation+7.98e-01

Pos logit contributions
oved+0.038
zed+0.037
opes+0.036
ths+0.034
iously+0.033
Neg logit contributions
ulu-0.039
J-0.038
ory-0.038
 Jill-0.035
 common-0.035
Token a
Token ID257
Feature activation+1.78e+00

Pos logit contributions
ulu+0.023
ory+0.023
J+0.022
ola+0.020
 common+0.019
Neg logit contributions
oved-0.030
zed-0.030
opes-0.029
ths-0.028
iously-0.028
Token time
Token ID640
Feature activation+5.15e+00

Pos logit contributions
ulu+0.057
ory+0.055
J+0.054
 Jill+0.051
 common+0.050
Neg logit contributions
oved-0.061
zed-0.059
opes-0.056
ths-0.055
iously-0.053
Token.
Token ID13
Feature activation-9.50e-02

Pos logit contributions
ulu+0.147
J+0.143
ory+0.141
 Jill+0.131
 common+0.129
Neg logit contributions
oved-0.199
zed-0.193
opes-0.192
ths-0.180
iously-0.178
Token
Token ID220
Feature activation-1.48e+00

Pos logit contributions
oved+0.003
zed+0.003
opes+0.003
ths+0.002
iously+0.002
Neg logit contributions
ulu-0.004
J-0.004
ory-0.004
 Jill-0.003
 common-0.003
Token
Token ID198
Feature activation+3.09e-01

Pos logit contributions
oved+0.068
zed+0.066
opes+0.065
ths+0.063
iously+0.063
Neg logit contributions
ulu-0.032
J-0.031
ory-0.030
 Jill-0.028
 common-0.027
Token
Token ID198
Feature activation+2.98e-01

Pos logit contributions
ory+0.009
ulu+0.009
J+0.008
 common+0.008
 Jill+0.007
Neg logit contributions
zed-0.012
oved-0.012
opes-0.011
ths-0.011
iously-0.010
TokenOnce
Token ID7454
Feature activation+2.72e-01

Pos logit contributions
ulu+0.011
ory+0.010
J+0.010
 Jill+0.010
 common+0.009
Neg logit contributions
oved-0.009
zed-0.009
opes-0.009
ths-0.008
iously-0.008
Token They
Token ID1119
Feature activation+5.15e-03

Pos logit contributions
ulu+0.000
ory+0.000
J+0.000
ora+0.000
ola+0.000
Neg logit contributions
oved-0.000
opes-0.000
zed-0.000
sed-0.000
 meanings-0.000
Token have
Token ID423
Feature activation+6.15e-01

Pos logit contributions
ulu+0.000
J+0.000
ory+0.000
 Jill+0.000
 common+0.000
Neg logit contributions
oved-0.000
zed-0.000
opes-0.000
ths-0.000
iously-0.000
Token many
Token ID867
Feature activation-3.56e-02

Pos logit contributions
ulu+0.020
J+0.019
ory+0.019
 common+0.018
 Jill+0.018
Neg logit contributions
oved-0.022
zed-0.021
opes-0.021
ths-0.019
iously-0.019
Token things
Token ID1243
Feature activation-7.07e-02

Pos logit contributions
zed+0.001
oved+0.001
opes+0.001
iously+0.001
sed+0.001
Neg logit contributions
J-0.001
ulu-0.001
 common-0.001
ory-0.001
 Jill-0.001
Token in
Token ID287
Feature activation+8.51e-01

Pos logit contributions
oved+0.002
zed+0.002
opes+0.002
ths+0.002
iously+0.002
Neg logit contributions
ulu-0.003
J-0.002
ory-0.002
 common-0.002
 Jill-0.002
Token common
Token ID2219
Feature activation+5.11e+00

Pos logit contributions
ory+0.023
ulu+0.021
J+0.018
ora+0.017
ackers+0.017
Neg logit contributions
oved-0.033
zed-0.032
opes-0.031
 meanings-0.030
ths-0.029
Token.
Token ID13
Feature activation+4.11e-02

Pos logit contributions
ulu+0.151
ory+0.144
J+0.143
 Jill+0.129
 common+0.128
Neg logit contributions
oved-0.197
opes-0.189
zed-0.188
iously-0.176
ths-0.174
Token They
Token ID1119
Feature activation+1.34e-01

Pos logit contributions
ulu+0.002
ory+0.002
J+0.001
ora+0.001
 mer+0.001
Neg logit contributions
oved-0.001
opes-0.001
 Leave-0.001
zed-0.001
 meanings-0.001
Token like
Token ID588
Feature activation+1.40e+00

Pos logit contributions
ulu+0.004
J+0.004
ory+0.004
 Jill+0.003
 common+0.003
Neg logit contributions
oved-0.005
opes-0.005
zed-0.005
ths-0.005
 meanings-0.005
Token the
Token ID262
Feature activation+2.88e-02

Pos logit contributions
ulu+0.047
J+0.046
ory+0.045
 Jill+0.042
 common+0.042
Neg logit contributions
oved-0.047
zed-0.046
opes-0.045
ths-0.042
iously-0.042
Token same
Token ID976
Feature activation+1.23e+00

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
iously-0.001
ths-0.001
Token They
Token ID1119
Feature activation-5.02e-01

Pos logit contributions
oved+0.009
 Leave+0.009
opes+0.009
zed+0.009
sed+0.008
Neg logit contributions
ory-0.014
ulu-0.013
J-0.012
ora-0.012
ola-0.012
Token have
Token ID423
Feature activation-7.96e-02

Pos logit contributions
oved+0.017
opes+0.017
zed+0.017
 meanings+0.016
sed+0.015
Neg logit contributions
J-0.016
ulu-0.016
ory-0.015
 Jill-0.014
ola-0.013
Token a
Token ID257
Feature activation-6.23e-01

Pos logit contributions
oved+0.004
zed+0.003
opes+0.003
iously+0.003
ths+0.003
Neg logit contributions
J-0.002
ulu-0.002
 Jill-0.002
ory-0.002
 common-0.002
Token lot
Token ID1256
Feature activation+7.53e-01

Pos logit contributions
sed+0.016
oved+0.015
zed+0.014
 ow+0.014
 meanings+0.013
Neg logit contributions
ulu-0.024
ola-0.023
ory-0.023
J-0.023
ill-0.022
Token in
Token ID287
Feature activation+4.19e-01

Pos logit contributions
ory+0.029
ulu+0.029
J+0.027
 Nina+0.026
ora+0.026
Neg logit contributions
oved-0.022
zed-0.018
der-0.018
opes-0.018
chair-0.018
Token common
Token ID2219
Feature activation+5.04e+00

Pos logit contributions
ory+0.016
ulu+0.015
ola+0.013
ora+0.013
va+0.013
Neg logit contributions
oved-0.012
opes-0.012
zed-0.012
 ow-0.011
 meanings-0.011
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
ulu+0.148
ory+0.142
J+0.140
 Jill+0.127
 common+0.124
Neg logit contributions
oved-0.196
opes-0.188
zed-0.187
iously-0.174
ths-0.173
Token They
Token ID1119
Feature activation-1.53e-01

Pos logit contributions
oved+0.005
opes+0.005
 Leave+0.005
sed+0.005
 meanings+0.005
Neg logit contributions
ory-0.007
ulu-0.007
ora-0.007
J-0.007
ola-0.006
Token become
Token ID1716
Feature activation+8.53e-01

Pos logit contributions
oved+0.005
opes+0.005
zed+0.005
 meanings+0.005
sed+0.005
Neg logit contributions
J-0.005
ulu-0.005
ory-0.005
 Jill-0.004
ola-0.004
Token friends
Token ID2460
Feature activation-1.92e-01

Pos logit contributions
ulu+0.035
ory+0.034
J+0.033
ola+0.032
va+0.031
Neg logit contributions
oved-0.019
opes-0.019
aged-0.018
 muscles-0.017
ths-0.016
Token.
Token ID13
Feature activation-2.44e-01

Pos logit contributions
oved+0.008
zed+0.007
opes+0.007
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 common-0.005
 Jill-0.005
Token He
Token ID679
Feature activation+2.39e-01

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token searched
Token ID16499
Feature activation+6.61e-01

Pos logit contributions
ulu+0.007
J+0.007
ory+0.007
 common+0.006
 Jill+0.006
Neg logit contributions
oved-0.009
zed-0.009
opes-0.009
ths-0.008
iously-0.008
Token for
Token ID329
Feature activation-5.49e-01

Pos logit contributions
ulu+0.023
J+0.022
ory+0.022
ola+0.020
 common+0.020
Neg logit contributions
oved-0.021
zed-0.020
opes-0.020
iously-0.019
ths-0.019
Token a
Token ID257
Feature activation+1.39e+00

Pos logit contributions
zed+0.018
oved+0.017
iously+0.017
opes+0.017
 ow+0.016
Neg logit contributions
ory-0.018
ulu-0.018
ora-0.017
J-0.017
 common-0.016
Token long
Token ID890
Feature activation+6.14e-01

Pos logit contributions
ulu+0.046
J+0.045
ory+0.044
 Jill+0.044
ola+0.042
Neg logit contributions
zed-0.038
oved-0.037
sed-0.037
ze-0.036
Days-0.035
Token time
Token ID640
Feature activation+5.04e+00

Pos logit contributions
ulu+0.021
J+0.021
ory+0.021
ola+0.020
 Av+0.019
Neg logit contributions
zed-0.019
oved-0.018
opes-0.016
iously-0.016
sed-0.015
Token but
Token ID475
Feature activation+2.40e-01

Pos logit contributions
ulu+0.168
ory+0.164
J+0.161
 common+0.152
ora+0.144
Neg logit contributions
oved-0.171
zed-0.162
opes-0.159
iously-0.154
ths-0.149
Token he
Token ID339
Feature activation-6.33e-01

Pos logit contributions
ulu+0.007
ory+0.007
J+0.007
 common+0.007
 Jill+0.006
Neg logit contributions
oved-0.009
zed-0.009
opes-0.008
ths-0.008
iously-0.008
Token couldn
Token ID3521
Feature activation-1.44e+00

Pos logit contributions
oved+0.017
zed+0.017
opes+0.016
ths+0.015
iously+0.015
Neg logit contributions
ulu-0.025
J-0.025
ory-0.025
 common-0.023
 Jill-0.023
Token't
Token ID470
Feature activation+1.68e+00

Pos logit contributions
oved+0.041
zed+0.039
opes+0.039
ths+0.036
iously+0.036
Neg logit contributions
ulu-0.055
J-0.054
ory-0.054
 common-0.050
 Jill-0.050
Token find
Token ID1064
Feature activation+4.82e-01

Pos logit contributions
ulu+0.045
J+0.044
ory+0.044
 common+0.041
 Jill+0.039
Neg logit contributions
oved-0.066
zed-0.064
opes-0.060
iously-0.060
ths-0.057
Token up
Token ID510
Feature activation-5.29e-01

Pos logit contributions
ory+0.008
ulu+0.008
J+0.008
ackers+0.008
rust+0.007
Neg logit contributions
zed-0.005
oved-0.005
erved-0.005
iously-0.005
ths-0.004
Token one
Token ID530
Feature activation+1.69e+00

Pos logit contributions
oved+0.017
zed+0.017
opes+0.016
iously+0.016
ths+0.016
Neg logit contributions
ulu-0.018
ory-0.018
J-0.017
ola-0.016
 common-0.015
Token step
Token ID2239
Feature activation-1.17e+00

Pos logit contributions
ulu+0.048
ory+0.047
J+0.047
 common+0.043
 Jill+0.041
Neg logit contributions
oved-0.066
zed-0.062
ths-0.060
opes-0.059
iously-0.058
Token at
Token ID379
Feature activation+5.07e-01

Pos logit contributions
oved+0.035
zed+0.032
iously+0.031
ths+0.030
opes+0.029
Neg logit contributions
ulu-0.043
 common-0.042
ory-0.042
J-0.041
 Jill-0.038
Token a
Token ID257
Feature activation+1.76e+00

Pos logit contributions
ulu+0.015
ory+0.015
J+0.014
ora+0.013
ola+0.013
Neg logit contributions
oved-0.018
zed-0.018
opes-0.018
iously-0.017
ths-0.017
Token time
Token ID640
Feature activation+5.04e+00

Pos logit contributions
ulu+0.058
ory+0.056
J+0.055
 Jill+0.050
ola+0.050
Neg logit contributions
oved-0.058
zed-0.057
opes-0.054
ths-0.053
ze-0.052
Token,
Token ID11
Feature activation+2.59e-01

Pos logit contributions
ulu+0.142
J+0.138
ory+0.136
 Jill+0.126
 common+0.125
Neg logit contributions
oved-0.195
zed-0.190
opes-0.188
ths-0.178
iously-0.176
Token and
Token ID290
Feature activation+6.75e-01

Pos logit contributions
ulu+0.008
J+0.008
ory+0.008
 Jill+0.007
 common+0.007
Neg logit contributions
oved-0.009
zed-0.009
opes-0.009
ths-0.008
iously-0.008
Token slowly
Token ID6364
Feature activation-1.04e+00

Pos logit contributions
ulu+0.019
J+0.019
ory+0.018
 Jill+0.018
 common+0.017
Neg logit contributions
oved-0.026
opes-0.025
zed-0.025
iously-0.023
ths-0.023
Token,
Token ID11
Feature activation-2.53e-01

Pos logit contributions
oved+0.038
zed+0.037
opes+0.036
ths+0.035
iously+0.035
Neg logit contributions
ulu-0.032
ory-0.031
J-0.031
 common-0.028
 Jill-0.028
Token the
Token ID262
Feature activation-8.94e-03

Pos logit contributions
oved+0.009
opes+0.009
zed+0.009
ths+0.008
iously+0.008
Neg logit contributions
ulu-0.008
J-0.008
ory-0.007
 Jill-0.007
 common-0.007
Token had
Token ID550
Feature activation-2.09e-01

Pos logit contributions
oved+0.022
opes+0.022
zed+0.021
ths+0.020
iously+0.020
Neg logit contributions
ulu-0.016
ory-0.015
J-0.015
 Jill-0.014
 common-0.014
Token lots
Token ID6041
Feature activation-4.45e-01

Pos logit contributions
oved+0.007
zed+0.007
opes+0.007
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.007
J-0.006
ory-0.006
 common-0.006
 Jill-0.006
Token of
Token ID286
Feature activation-2.43e-01

Pos logit contributions
oved+0.017
zed+0.016
opes+0.016
ths+0.015
iously+0.015
Neg logit contributions
ulu-0.013
J-0.013
ory-0.013
 common-0.012
 Jill-0.012
Token things
Token ID1243
Feature activation+4.80e-02

Pos logit contributions
oved+0.008
zed+0.008
opes+0.008
 meanings+0.007
iously+0.007
Neg logit contributions
ulu-0.008
ory-0.008
J-0.008
ora-0.007
 Jill-0.007
Token in
Token ID287
Feature activation+7.83e-01

Pos logit contributions
ulu+0.002
J+0.002
ory+0.002
 common+0.001
 Jill+0.001
Neg logit contributions
oved-0.002
zed-0.002
opes-0.001
ths-0.001
iously-0.001
Token common
Token ID2219
Feature activation+5.01e+00

Pos logit contributions
ulu+0.024
ory+0.024
J+0.021
ora+0.020
ola+0.019
Neg logit contributions
zed-0.028
oved-0.027
opes-0.025
ths-0.024
 meanings-0.023
Token,
Token ID11
Feature activation+8.25e-01

Pos logit contributions
ulu+0.148
J+0.141
ory+0.140
 common+0.127
 Jill+0.127
Neg logit contributions
oved-0.193
zed-0.185
opes-0.184
iously-0.172
ths-0.171
Token like
Token ID588
Feature activation+2.09e+00

Pos logit contributions
ulu+0.027
ory+0.026
J+0.026
 common+0.024
ola+0.023
Neg logit contributions
oved-0.029
zed-0.028
opes-0.027
iously-0.025
ths-0.025
Token his
Token ID465
Feature activation-7.60e-01

Pos logit contributions
ulu+0.066
ory+0.064
J+0.063
 common+0.058
 Jill+0.056
Neg logit contributions
oved-0.075
zed-0.073
opes-0.071
ths-0.067
iously-0.067
Token love
Token ID1842
Feature activation+1.72e+00

Pos logit contributions
oved+0.026
zed+0.025
opes+0.025
sed+0.023
iously+0.023
Neg logit contributions
ulu-0.025
J-0.024
ory-0.024
 Jill-0.022
 common-0.021
Token for
Token ID329
Feature activation-1.10e+00

Pos logit contributions
ulu+0.054
J+0.052
ory+0.051
 common+0.047
 Jill+0.046
Neg logit contributions
oved-0.063
zed-0.061
opes-0.059
ths-0.056
iously-0.056
Token,
Token ID11
Feature activation-6.40e-02

Pos logit contributions
oved+0.042
zed+0.042
iously+0.041
ths+0.040
opes+0.038
Neg logit contributions
ory-0.052
ulu-0.048
ackers-0.046
J-0.045
emo-0.044
Token one
Token ID530
Feature activation+1.83e+00

Pos logit contributions
oved+0.002
zed+0.002
opes+0.002
ths+0.002
iously+0.002
Neg logit contributions
ulu-0.002
J-0.002
ory-0.002
 Jill-0.002
 common-0.002
Token step
Token ID2239
Feature activation-1.07e+00

Pos logit contributions
ulu+0.052
ory+0.051
J+0.051
 common+0.046
 Jill+0.045
Neg logit contributions
oved-0.072
zed-0.069
opes-0.068
ths-0.065
iously-0.065
Token at
Token ID379
Feature activation+7.35e-01

Pos logit contributions
oved+0.034
zed+0.033
opes+0.031
iously+0.031
ths+0.031
Neg logit contributions
ulu-0.037
ory-0.036
J-0.035
 common-0.035
 Jill-0.033
Token a
Token ID257
Feature activation+1.64e+00

Pos logit contributions
ory+0.024
ulu+0.023
J+0.022
ola+0.021
 common+0.020
Neg logit contributions
zed-0.024
oved-0.023
opes-0.023
iously-0.022
ths-0.022
Token time
Token ID640
Feature activation+4.99e+00

Pos logit contributions
ulu+0.054
ory+0.054
J+0.052
ola+0.049
 Jill+0.049
Neg logit contributions
oved-0.052
zed-0.052
opes-0.049
 ow-0.047
ze-0.047
Token.
Token ID13
Feature activation+4.15e-01

Pos logit contributions
ulu+0.143
J+0.138
ory+0.137
 common+0.125
 Jill+0.125
Neg logit contributions
oved-0.193
zed-0.187
opes-0.185
ths-0.175
iously-0.174
Token
Token ID198
Feature activation+4.64e-01

Pos logit contributions
ulu+0.013
ory+0.012
J+0.012
 common+0.011
 Jill+0.011
Neg logit contributions
oved-0.015
zed-0.015
opes-0.015
ths-0.014
iously-0.014
Token
Token ID198
Feature activation+4.42e-01

Pos logit contributions
ory+0.014
ulu+0.013
J+0.012
 common+0.012
 Jill+0.012
Neg logit contributions
zed-0.017
oved-0.017
opes-0.016
ths-0.015
aged-0.015
TokenTheir
Token ID14574
Feature activation-7.09e-01

Pos logit contributions
ory+0.016
ulu+0.015
J+0.014
 Jill+0.014
 common+0.014
Neg logit contributions
zed-0.014
oved-0.014
opes-0.013
ths-0.013
erved-0.012
Token mom
Token ID1995
Feature activation-6.00e-01

Pos logit contributions
oved+0.033
zed+0.032
opes+0.031
iously+0.030
ths+0.029
Neg logit contributions
J-0.015
ulu-0.014
ory-0.014
 Jill-0.014
 common-0.013
Token the
Token ID262
Feature activation+6.41e-01

Pos logit contributions
oved+0.019
zed+0.019
opes+0.019
ths+0.018
iously+0.018
Neg logit contributions
ulu-0.012
J-0.011
ory-0.011
 common-0.010
 Jill-0.010
Token books
Token ID3835
Feature activation-3.33e-01

Pos logit contributions
J+0.019
ory+0.017
ulu+0.017
 Jill+0.017
 common+0.017
Neg logit contributions
zed-0.023
oved-0.023
ths-0.022
opes-0.022
iously-0.021
Token one
Token ID530
Feature activation+2.10e+00

Pos logit contributions
opes+0.013
oved+0.013
zed+0.013
sed+0.012
ths+0.012
Neg logit contributions
ulu-0.009
J-0.009
ory-0.008
 Jill-0.008
 common-0.007
Token at
Token ID379
Feature activation+1.21e+00

Pos logit contributions
ulu+0.057
J+0.055
ory+0.054
 Jill+0.051
 common+0.050
Neg logit contributions
oved-0.083
zed-0.082
opes-0.081
iously-0.075
sed-0.075
Token a
Token ID257
Feature activation+1.75e+00

Pos logit contributions
ulu+0.034
ory+0.034
J+0.032
 common+0.029
ola+0.028
Neg logit contributions
oved-0.047
zed-0.045
opes-0.045
ths-0.043
iously-0.043
Token time
Token ID640
Feature activation+4.99e+00

Pos logit contributions
ulu+0.051
ory+0.049
J+0.049
 common+0.045
 Jill+0.045
Neg logit contributions
oved-0.067
zed-0.065
opes-0.064
ths-0.060
iously-0.060
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
ulu+0.136
J+0.133
ory+0.130
 Jill+0.121
 common+0.119
Neg logit contributions
oved-0.197
zed-0.193
opes-0.190
ths-0.180
iously-0.178
Token In
Token ID554
Feature activation+9.39e-01

Pos logit contributions
oved+0.005
zed+0.005
opes+0.005
ths+0.004
iously+0.004
Neg logit contributions
ulu-0.006
J-0.006
 Jill-0.006
ory-0.006
 Jenny-0.006
Token each
Token ID1123
Feature activation-1.89e-01

Pos logit contributions
ulu+0.024
ory+0.023
J+0.023
 common+0.020
 Jill+0.020
Neg logit contributions
oved-0.040
zed-0.039
opes-0.038
ths-0.036
iously-0.036
Token book
Token ID1492
Feature activation+2.07e-01

Pos logit contributions
oved+0.008
zed+0.008
opes+0.007
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 common-0.004
 Jill-0.004
Token she
Token ID673
Feature activation-6.85e-01

Pos logit contributions
ulu+0.005
J+0.005
 Jill+0.005
ory+0.005
 common+0.005
Neg logit contributions
oved-0.008
zed-0.008
opes-0.008
iously-0.008
ths-0.008
Token had
Token ID550
Feature activation-1.48e-01

Pos logit contributions
oved+0.030
opes+0.029
zed+0.029
ths+0.028
iously+0.028
Neg logit contributions
ulu-0.021
ory-0.020
J-0.020
 Jill-0.019
 common-0.018
Token lots
Token ID6041
Feature activation-5.50e-01

Pos logit contributions
oved+0.005
zed+0.005
opes+0.005
ths+0.005
iously+0.005
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 common-0.004
 Jill-0.004
Token of
Token ID286
Feature activation-3.17e-01

Pos logit contributions
oved+0.020
zed+0.019
opes+0.019
ths+0.018
iously+0.018
Neg logit contributions
ulu-0.017
J-0.016
ory-0.016
 common-0.015
 Jill-0.015
Token things
Token ID1243
Feature activation-9.37e-02

Pos logit contributions
oved+0.011
opes+0.010
zed+0.010
 meanings+0.009
iously+0.009
Neg logit contributions
ulu-0.011
ory-0.010
J-0.010
ora-0.009
 Jill-0.009
Token in
Token ID287
Feature activation+6.35e-01

Pos logit contributions
oved+0.003
zed+0.003
opes+0.003
ths+0.003
iously+0.003
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 common-0.003
 Jill-0.003
Token common
Token ID2219
Feature activation+4.90e+00

Pos logit contributions
ulu+0.019
ory+0.019
J+0.016
ora+0.016
ola+0.015
Neg logit contributions
zed-0.023
oved-0.023
opes-0.021
ths-0.020
 meanings-0.020
Token,
Token ID11
Feature activation+8.44e-01

Pos logit contributions
ulu+0.143
J+0.136
ory+0.136
 common+0.123
 Jill+0.123
Neg logit contributions
oved-0.190
zed-0.182
opes-0.181
iously-0.170
ths-0.168
Token like
Token ID588
Feature activation+1.92e+00

Pos logit contributions
ulu+0.028
ory+0.027
J+0.026
 common+0.024
ola+0.024
Neg logit contributions
oved-0.029
zed-0.029
opes-0.028
iously-0.026
ths-0.026
Token his
Token ID465
Feature activation-1.01e+00

Pos logit contributions
ulu+0.060
ory+0.059
J+0.058
 common+0.053
ora+0.051
Neg logit contributions
oved-0.069
zed-0.067
opes-0.066
ths-0.062
iously-0.061
Token love
Token ID1842
Feature activation+1.49e+00

Pos logit contributions
oved+0.036
zed+0.034
opes+0.034
sed+0.031
iously+0.031
Neg logit contributions
ulu-0.033
J-0.032
ory-0.031
 common-0.029
 Jill-0.028
Token for
Token ID329
Feature activation-1.26e+00

Pos logit contributions
ulu+0.046
J+0.044
ory+0.044
 common+0.040
 Jill+0.039
Neg logit contributions
oved-0.055
zed-0.053
opes-0.052
ths-0.049
iously-0.049
Token,
Token ID11
Feature activation+3.38e-02

Pos logit contributions
oved+0.025
zed+0.024
opes+0.024
ths+0.023
iously+0.022
Neg logit contributions
ulu-0.017
J-0.016
ory-0.016
 Jill-0.015
 common-0.015
Token one
Token ID530
Feature activation+1.84e+00

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token number
Token ID1271
Feature activation+9.80e-01

Pos logit contributions
ulu+0.044
 Jill+0.043
J+0.042
ory+0.042
 common+0.038
Neg logit contributions
opes-0.076
zed-0.075
oved-0.075
erved-0.071
sed-0.069
Token at
Token ID379
Feature activation+5.99e-01

Pos logit contributions
ulu+0.029
J+0.028
ory+0.028
 Jill+0.026
 common+0.026
Neg logit contributions
oved-0.037
zed-0.036
opes-0.035
ths-0.033
iously-0.033
Token a
Token ID257
Feature activation+1.60e+00

Pos logit contributions
ulu+0.019
ory+0.019
J+0.018
 common+0.017
ola+0.016
Neg logit contributions
oved-0.021
opes-0.021
zed-0.020
ths-0.019
iously-0.019
Token time
Token ID640
Feature activation+4.88e+00

Pos logit contributions
ulu+0.050
J+0.047
ory+0.047
ola+0.043
 common+0.042
Neg logit contributions
oved-0.058
zed-0.056
opes-0.054
ths-0.052
iously-0.051
Token.
Token ID13
Feature activation+3.32e-01

Pos logit contributions
ulu+0.139
ory+0.134
J+0.133
 common+0.122
 Jill+0.120
Neg logit contributions
oved-0.190
zed-0.183
opes-0.181
ths-0.172
iously-0.171
Token
Token ID198
Feature activation+3.11e-01

Pos logit contributions
ulu+0.012
ory+0.011
J+0.011
 common+0.010
ola+0.010
Neg logit contributions
oved-0.011
zed-0.011
opes-0.010
iously-0.010
ths-0.010
Token
Token ID198
Feature activation+3.15e-01

Pos logit contributions
ory+0.008
ulu+0.008
J+0.008
 common+0.007
 Jill+0.007
Neg logit contributions
oved-0.012
zed-0.012
opes-0.012
ths-0.011
iously-0.011
TokenAs
Token ID1722
Feature activation+2.98e-01

Pos logit contributions
ulu+0.012
ory+0.012
J+0.011
 Jill+0.011
 common+0.011
Neg logit contributions
oved-0.009
zed-0.009
opes-0.009
ths-0.008
iously-0.008
Token he
Token ID339
Feature activation-1.89e+00

Pos logit contributions
ulu+0.010
ory+0.010
ora+0.009
ola+0.009
J+0.009
Neg logit contributions
zed-0.010
ths-0.010
oved-0.009
iously-0.008
opes-0.008
Token,
Token ID11
Feature activation-2.32e-01

Pos logit contributions
zed+0.012
oved+0.012
opes+0.012
sed+0.011
ths+0.011
Neg logit contributions
ulu-0.006
J-0.006
 Jill-0.006
ory-0.006
 common-0.005
Token one
Token ID530
Feature activation+1.88e+00

Pos logit contributions
oved+0.010
opes+0.009
zed+0.009
ths+0.008
iously+0.008
Neg logit contributions
ulu-0.006
J-0.006
ory-0.006
 Jill-0.006
 common-0.005
Token step
Token ID2239
Feature activation-7.92e-01

Pos logit contributions
ulu+0.044
 Jill+0.039
J+0.038
 deeper+0.036
 closer+0.035
Neg logit contributions
opes-0.086
zed-0.084
oved-0.082
sed-0.076
erved-0.075
Token at
Token ID379
Feature activation+7.47e-01

Pos logit contributions
oved+0.028
zed+0.028
opes+0.027
ths+0.025
iously+0.025
Neg logit contributions
ulu-0.025
J-0.024
ory-0.024
 Jill-0.022
 common-0.022
Token a
Token ID257
Feature activation+1.57e+00

Pos logit contributions
ory+0.021
ulu+0.021
J+0.020
 common+0.018
ola+0.017
Neg logit contributions
oved-0.029
zed-0.028
opes-0.028
ths-0.027
iously-0.027
Token time
Token ID640
Feature activation+4.86e+00

Pos logit contributions
ulu+0.048
ory+0.048
J+0.047
 Jill+0.043
 common+0.043
Neg logit contributions
oved-0.056
zed-0.055
opes-0.053
ths-0.051
iously-0.050
Token.
Token ID13
Feature activation+2.83e-03

Pos logit contributions
ulu+0.119
J+0.116
ory+0.110
 Jill+0.108
 common+0.101
Neg logit contributions
oved-0.204
zed-0.203
opes-0.202
ths-0.189
erved-0.186
Token They
Token ID1119
Feature activation-8.85e-02

Pos logit contributions
ulu+0.000
ory+0.000
J+0.000
 common+0.000
ola+0.000
Neg logit contributions
oved-0.000
zed-0.000
opes-0.000
sed-0.000
iously-0.000
Token looked
Token ID3114
Feature activation+1.41e-02

Pos logit contributions
oved+0.003
opes+0.003
zed+0.003
iously+0.003
ths+0.003
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 Jill-0.002
 common-0.002
Token at
Token ID379
Feature activation-4.34e-01

Pos logit contributions
ulu+0.000
ory+0.000
J+0.000
 Jill+0.000
 common+0.000
Neg logit contributions
oved-0.000
zed-0.000
opes-0.000
ths-0.000
iously-0.000
Token the
Token ID262
Feature activation+7.24e-01

Pos logit contributions
oved+0.020
zed+0.019
opes+0.019
ths+0.018
iously+0.018
Neg logit contributions
ulu-0.010
J-0.009
ory-0.009
 Jill-0.009
 common-0.009
Token,
Token ID11
Feature activation-1.81e-01

Pos logit contributions
oved+0.008
zed+0.008
opes+0.008
iously+0.007
ths+0.007
Neg logit contributions
ulu-0.007
ory-0.007
J-0.006
 common-0.006
 Jill-0.006
Token one
Token ID530
Feature activation+2.20e+00

Pos logit contributions
oved+0.007
opes+0.007
zed+0.006
ths+0.006
iously+0.006
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 Jill-0.005
 common-0.005
Token step
Token ID2239
Feature activation-5.93e-01

Pos logit contributions
ulu+0.059
J+0.056
ory+0.053
 Jill+0.052
ola+0.049
Neg logit contributions
opes-0.091
oved-0.090
zed-0.088
iously-0.082
sed-0.082
Token at
Token ID379
Feature activation+5.13e-01

Pos logit contributions
oved+0.019
zed+0.019
opes+0.018
iously+0.017
ths+0.017
Neg logit contributions
ulu-0.020
ory-0.020
J-0.020
 common-0.019
 Jill-0.018
Token a
Token ID257
Feature activation+1.25e+00

Pos logit contributions
ory+0.015
ulu+0.015
J+0.014
 common+0.013
ola+0.013
Neg logit contributions
oved-0.019
zed-0.019
opes-0.018
iously-0.018
ths-0.018
Token time
Token ID640
Feature activation+4.86e+00

Pos logit contributions
ulu+0.040
ory+0.040
J+0.039
 Jill+0.036
 common+0.035
Neg logit contributions
oved-0.043
zed-0.042
opes-0.039
ths-0.039
iously-0.038
Token.
Token ID13
Feature activation-3.50e-01

Pos logit contributions
ulu+0.136
J+0.132
ory+0.129
 Jill+0.121
 common+0.118
Neg logit contributions
oved-0.189
zed-0.184
opes-0.183
ths-0.172
iously-0.170
Token
Token ID220
Feature activation-1.21e+00

Pos logit contributions
oved+0.009
zed+0.008
opes+0.008
iously+0.007
ths+0.007
Neg logit contributions
ulu-0.014
ory-0.014
J-0.014
 common-0.014
ola-0.013
Token
Token ID198
Feature activation+3.03e-01

Pos logit contributions
oved+0.052
zed+0.050
opes+0.050
ths+0.047
iously+0.047
Neg logit contributions
ulu-0.029
ory-0.028
J-0.028
 common-0.025
 Jill-0.025
Token
Token ID198
Feature activation+2.76e-01

Pos logit contributions
ory+0.010
ulu+0.009
 common+0.009
 mer+0.008
 shrimp+0.008
Neg logit contributions
zed-0.010
oved-0.010
opes-0.009
ths-0.009
ending-0.009
TokenWhen
Token ID2215
Feature activation+6.27e-01

Pos logit contributions
ory+0.011
ulu+0.010
 common+0.010
 Jill+0.009
J+0.009
Neg logit contributions
oved-0.008
zed-0.008
ths-0.007
opes-0.007
ending-0.006
Token One
Token ID1881
Feature activation+8.88e-01

Pos logit contributions
oved+0.009
zed+0.009
opes+0.009
ths+0.008
iously+0.008
Neg logit contributions
ulu-0.011
J-0.011
ory-0.011
 common-0.010
 Jill-0.010
Token slow
Token ID3105
Feature activation+1.01e+00

Pos logit contributions
ulu+0.024
J+0.022
ory+0.021
 Jill+0.021
 common+0.020
Neg logit contributions
oved-0.037
opes-0.037
zed-0.036
iously-0.034
sed-0.034
Token step
Token ID2239
Feature activation-8.36e-01

Pos logit contributions
ulu+0.031
J+0.030
ory+0.030
 common+0.027
 Jill+0.027
Neg logit contributions
oved-0.037
zed-0.036
opes-0.036
ths-0.034
iously-0.034
Token at
Token ID379
Feature activation+3.84e-01

Pos logit contributions
oved+0.025
zed+0.024
opes+0.023
ths+0.022
iously+0.022
Neg logit contributions
ulu-0.030
ory-0.030
J-0.030
 common-0.028
 Jill-0.027
Token a
Token ID257
Feature activation+1.31e+00

Pos logit contributions
ory+0.012
ulu+0.012
J+0.012
 common+0.011
 mer+0.011
Neg logit contributions
oved-0.012
zed-0.012
ths-0.012
opes-0.012
iously-0.012
Token time
Token ID640
Feature activation+4.82e+00

Pos logit contributions
ulu+0.041
ory+0.040
J+0.039
 common+0.036
 Jill+0.036
Neg logit contributions
oved-0.045
zed-0.044
ths-0.042
opes-0.041
iously-0.040
Token,
Token ID11
Feature activation+3.00e-01

Pos logit contributions
ulu+0.138
J+0.133
ory+0.132
 Jill+0.122
 common+0.121
Neg logit contributions
oved-0.186
zed-0.181
opes-0.179
ths-0.168
iously-0.167
Token she
Token ID673
Feature activation-2.82e-01

Pos logit contributions
ulu+0.009
ory+0.009
J+0.009
 common+0.008
ola+0.008
Neg logit contributions
oved-0.011
zed-0.010
opes-0.010
ths-0.010
iously-0.010
Token followed
Token ID3940
Feature activation-6.89e-01

Pos logit contributions
oved+0.010
zed+0.010
opes+0.010
ths+0.009
iously+0.009
Neg logit contributions
ulu-0.008
J-0.008
ory-0.008
 Jill-0.008
 common-0.007
Token her
Token ID607
Feature activation-7.62e-01

Pos logit contributions
zed+0.022
oved+0.022
iously+0.021
ths+0.020
zy+0.020
Neg logit contributions
ulu-0.023
ory-0.022
J-0.021
 common-0.020
ackers-0.020
Token mom
Token ID1995
Feature activation-2.92e-01

Pos logit contributions
oved+0.031
zed+0.030
opes+0.030
iously+0.028
ths+0.028
Neg logit contributions
ulu-0.020
J-0.019
ory-0.019
 Jill-0.018
 common-0.018
Token wood
Token ID4898
Feature activation-6.61e-01

Pos logit contributions
opes+0.004
oved+0.004
zed+0.004
iously+0.004
ths+0.004
Neg logit contributions
ory-0.004
ulu-0.004
J-0.004
ola-0.004
 common-0.004
Token.
Token ID13
Feature activation+7.78e-02

Pos logit contributions
oved+0.025
zed+0.024
opes+0.023
ths+0.022
iously+0.022
Neg logit contributions
ulu-0.020
J-0.019
ory-0.019
 common-0.018
 Jill-0.017
Token One
Token ID1881
Feature activation+1.42e+00

Pos logit contributions
ulu+0.003
ory+0.003
J+0.003
 common+0.003
ora+0.003
Neg logit contributions
oved-0.002
zed-0.002
opes-0.002
iously-0.002
ths-0.002
Token day
Token ID1110
Feature activation+8.85e-01

Pos logit contributions
ulu+0.037
J+0.035
ory+0.035
 Jill+0.032
 common+0.032
Neg logit contributions
oved-0.059
zed-0.057
opes-0.057
iously-0.054
ths-0.054
Token a
Token ID257
Feature activation+5.14e-01

Pos logit contributions
ulu+0.027
ory+0.027
J+0.026
 common+0.024
ola+0.023
Neg logit contributions
oved-0.032
zed-0.031
opes-0.030
ths-0.028
iously-0.028
Token trou
Token ID4057
Feature activation+4.79e+00

Pos logit contributions
ulu+0.018
J+0.017
ory+0.017
ill+0.017
ola+0.017
Neg logit contributions
ths-0.014
sed-0.014
zed-0.013
oved-0.013
 ow-0.013
Tokenl
Token ID75
Feature activation-5.11e-01

Pos logit contributions
ory+0.170
ulu+0.161
J+0.155
 Jill+0.150
 common+0.150
Neg logit contributions
oved-0.157
zed-0.144
opes-0.140
ths-0.135
iously-0.130
Tokenbe
Token ID1350
Feature activation+1.62e+00

Pos logit contributions
zed+0.017
ths+0.016
opes+0.015
iously+0.015
oved+0.015
Neg logit contributions
ulu-0.018
J-0.016
ory-0.016
 Jill-0.015
ora-0.015
Token came
Token ID1625
Feature activation-2.44e-01

Pos logit contributions
ulu+0.058
ory+0.057
J+0.056
 common+0.053
 Jill+0.052
Neg logit contributions
oved-0.051
zed-0.050
opes-0.048
iously-0.045
ths-0.045
Token to
Token ID284
Feature activation-2.82e-01

Pos logit contributions
oved+0.008
zed+0.008
opes+0.008
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.008
J-0.008
ory-0.008
 common-0.007
 Jill-0.007
Token the
Token ID262
Feature activation+6.55e-01

Pos logit contributions
zed+0.010
oved+0.009
opes+0.009
iously+0.009
ths+0.009
Neg logit contributions
ulu-0.009
J-0.009
ory-0.008
ola-0.008
ora-0.007
Token She
Token ID1375
Feature activation-5.32e-01

Pos logit contributions
oved+0.007
zed+0.006
opes+0.006
ths+0.006
iously+0.006
Neg logit contributions
ulu-0.007
J-0.007
ory-0.007
 Jill-0.007
 common-0.006
Token searched
Token ID16499
Feature activation+2.08e-02

Pos logit contributions
oved+0.021
zed+0.021
opes+0.020
ths+0.019
iously+0.019
Neg logit contributions
ulu-0.015
J-0.014
ory-0.014
 common-0.013
 Jill-0.013
Token for
Token ID329
Feature activation-1.05e+00

Pos logit contributions
ulu+0.001
ory+0.001
J+0.001
 common+0.001
ola+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token a
Token ID257
Feature activation+1.02e+00

Pos logit contributions
zed+0.037
oved+0.036
opes+0.035
iously+0.034
ths+0.034
Neg logit contributions
ory-0.033
ulu-0.032
J-0.030
 common-0.029
ora-0.028
Token long
Token ID890
Feature activation+2.92e-01

Pos logit contributions
ulu+0.033
ory+0.032
J+0.031
 Jill+0.031
ola+0.030
Neg logit contributions
oved-0.031
zed-0.030
sed-0.029
ths-0.029
opes-0.029
Token time
Token ID640
Feature activation+4.78e+00

Pos logit contributions
ulu+0.009
J+0.009
ory+0.009
ola+0.009
 Jill+0.008
Neg logit contributions
oved-0.010
zed-0.010
opes-0.009
ths-0.009
iously-0.009
Token until
Token ID1566
Feature activation-3.36e-01

Pos logit contributions
ulu+0.156
ory+0.154
J+0.150
 common+0.142
 Jill+0.135
Neg logit contributions
oved-0.164
zed-0.155
opes-0.152
iously-0.146
ths-0.145
Token she
Token ID673
Feature activation-1.09e+00

Pos logit contributions
zed+0.012
oved+0.011
ths+0.011
iously+0.010
opes+0.010
Neg logit contributions
ory-0.011
ulu-0.010
J-0.010
 common-0.010
ora-0.009
Token found
Token ID1043
Feature activation+1.28e-01

Pos logit contributions
zed+0.037
oved+0.036
ths+0.033
opes+0.031
iously+0.031
Neg logit contributions
 common-0.035
ory-0.034
ulu-0.033
J-0.032
ora-0.030
Token something
Token ID1223
Feature activation+1.07e+00

Pos logit contributions
ory+0.004
ulu+0.004
J+0.004
 common+0.004
ola+0.003
Neg logit contributions
oved-0.005
zed-0.005
opes-0.004
iously-0.004
ths-0.004
Token incredible
Token ID8082
Feature activation+1.33e-02

Pos logit contributions
ory+0.035
ulu+0.035
J+0.035
 common+0.032
ora+0.031
Neg logit contributions
oved-0.035
zed-0.033
opes-0.032
ths-0.031
sed-0.031
Token day
Token ID1110
Feature activation-2.75e-01

Pos logit contributions
ulu+0.011
J+0.011
ory+0.011
 common+0.010
 Jill+0.010
Neg logit contributions
oved-0.017
zed-0.016
opes-0.016
ths-0.015
iously-0.015
Token,
Token ID11
Feature activation-5.59e-01

Pos logit contributions
oved+0.011
zed+0.011
opes+0.011
ths+0.010
iously+0.010
Neg logit contributions
ulu-0.007
ory-0.007
J-0.007
 common-0.006
 Jill-0.006
Token while
Token ID981
Feature activation-3.25e-01

Pos logit contributions
zed+0.023
oved+0.023
opes+0.022
ths+0.021
iously+0.021
Neg logit contributions
ulu-0.014
J-0.013
ory-0.013
ola-0.012
ora-0.012
Token Benny
Token ID44275
Feature activation-3.58e-01

Pos logit contributions
oved+0.009
zed+0.009
opes+0.008
ths+0.008
iously+0.008
Neg logit contributions
ulu-0.013
J-0.013
ory-0.013
 common-0.012
 Jill-0.012
Token was
Token ID373
Feature activation-1.03e+00

Pos logit contributions
oved+0.014
opes+0.014
zed+0.014
ths+0.013
iously+0.013
Neg logit contributions
ulu-0.010
ory-0.010
J-0.009
 common-0.008
 Jill-0.008
Token m
Token ID285
Feature activation-5.37e+00

Pos logit contributions
oved+0.039
opes+0.038
 meanings+0.036
ths+0.036
iously+0.035
Neg logit contributions
ulu-0.031
ory-0.028
J-0.027
 Jill-0.027
 mer-0.026
Tokenunch
Token ID3316
Feature activation-5.50e-01

Pos logit contributions
opes+0.172
zed+0.165
 meanings+0.159
oved+0.155
sed+0.153
Neg logit contributions
ulu-0.193
ory-0.191
J-0.173
ola-0.164
ora-0.157
Tokening
Token ID278
Feature activation-2.78e+00

Pos logit contributions
oved+0.015
zed+0.014
opes+0.013
ths+0.013
iously+0.012
Neg logit contributions
ulu-0.022
J-0.022
 common-0.021
ory-0.021
 Jill-0.021
Token on
Token ID319
Feature activation-1.89e+00

Pos logit contributions
oved+0.109
zed+0.105
opes+0.105
ths+0.099
iously+0.098
Neg logit contributions
ulu-0.077
ory-0.074
J-0.074
 common-0.068
 Jill-0.068
Token a
Token ID257
Feature activation+5.44e-01

Pos logit contributions
oved+0.079
zed+0.076
opes+0.075
ths+0.072
iously+0.071
Neg logit contributions
ulu-0.048
ory-0.046
J-0.046
 common-0.042
 Jill-0.042
Token carrot
Token ID40562
Feature activation-1.53e+00

Pos logit contributions
ulu+0.015
J+0.014
ory+0.014
 Jill+0.013
 common+0.013
Neg logit contributions
oved-0.022
zed-0.021
opes-0.021
ths-0.020
iously-0.020
Token They
Token ID1119
Feature activation-1.61e-01

Pos logit contributions
ulu+0.013
J+0.013
ory+0.012
 Jill+0.012
 common+0.011
Neg logit contributions
oved-0.021
zed-0.021
opes-0.020
ths-0.019
iously-0.019
Token did
Token ID750
Feature activation+2.89e-01

Pos logit contributions
oved+0.006
zed+0.006
opes+0.006
ths+0.005
iously+0.005
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 Jill-0.005
 common-0.004
Token not
Token ID407
Feature activation-1.54e-01

Pos logit contributions
ulu+0.009
J+0.009
 common+0.009
 Jill+0.009
ory+0.009
Neg logit contributions
oved-0.010
opes-0.010
zed-0.009
ths-0.009
iously-0.009
Token know
Token ID760
Feature activation-5.30e-02

Pos logit contributions
oved+0.004
 ow+0.004
ze+0.004
opes+0.003
zed+0.003
Neg logit contributions
ory-0.006
J-0.006
ulu-0.006
ola-0.005
ora-0.005
Token sun
Token ID4252
Feature activation-2.45e+00

Pos logit contributions
oved+0.002
zed+0.002
opes+0.002
erved+0.002
iously+0.002
Neg logit contributions
ulu-0.002
 Jill-0.002
J-0.002
 Jenny-0.001
ory-0.001
Tokenfl
Token ID2704
Feature activation-5.33e+00

Pos logit contributions
zed+0.084
oved+0.083
opes+0.077
iously+0.075
ths+0.074
Neg logit contributions
ulu-0.083
J-0.075
ory-0.074
 Jill-0.073
 common-0.069
Tokenowers
Token ID3618
Feature activation-2.46e+00

Pos logit contributions
zed+0.158
oved+0.135
iously+0.129
opes+0.127
ths+0.124
Neg logit contributions
ulu-0.222
ory-0.204
J-0.196
ola-0.193
ora-0.190
Token could
Token ID714
Feature activation+5.65e-01

Pos logit contributions
oved+0.100
zed+0.098
opes+0.096
ths+0.092
iously+0.092
Neg logit contributions
ulu-0.067
ory-0.062
J-0.059
 common-0.058
 Jill-0.057
Token talk
Token ID1561
Feature activation+4.20e-01

Pos logit contributions
ulu+0.015
J+0.014
ory+0.014
 common+0.013
 Jill+0.013
Neg logit contributions
oved-0.023
zed-0.022
opes-0.022
ths-0.021
iously-0.021
Token.
Token ID13
Feature activation+6.69e-02

Pos logit contributions
ulu+0.010
J+0.010
ory+0.010
 Jill+0.009
 common+0.009
Neg logit contributions
oved-0.017
zed-0.017
opes-0.017
ths-0.017
iously-0.016
Token
Token ID198
Feature activation-1.68e-03

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.003
zed-0.003
opes-0.003
iously-0.003
ths-0.003
Token She
Token ID1375
Feature activation-2.91e-01

Pos logit contributions
oved+0.006
zed+0.005
opes+0.005
sed+0.005
iously+0.005
Neg logit contributions
ulu-0.009
ory-0.008
J-0.008
 common-0.008
ola-0.008
Token did
Token ID750
Feature activation+3.27e-01

Pos logit contributions
oved+0.010
zed+0.010
opes+0.009
sed+0.009
ths+0.009
Neg logit contributions
ulu-0.009
ory-0.009
J-0.009
 common-0.009
ola-0.008
Token not
Token ID407
Feature activation-3.66e-01

Pos logit contributions
ory+0.015
ulu+0.015
J+0.014
ora+0.013
ola+0.013
Neg logit contributions
zed-0.008
oved-0.007
opes-0.007
ths-0.006
iously-0.006
Token know
Token ID760
Feature activation-2.88e-01

Pos logit contributions
 ow+0.008
oved+0.008
 meanings+0.007
 about+0.007
ze+0.007
Neg logit contributions
ulu-0.015
ola-0.015
ory-0.014
J-0.014
 Nina-0.014
Token sun
Token ID4252
Feature activation-2.52e+00

Pos logit contributions
oved+0.010
zed+0.009
opes+0.009
ths+0.009
iously+0.009
Neg logit contributions
ulu-0.010
J-0.009
ory-0.009
 Jill-0.009
 common-0.009
Tokenfl
Token ID2704
Feature activation-5.27e+00

Pos logit contributions
oved+0.082
zed+0.082
opes+0.077
ths+0.073
iously+0.073
Neg logit contributions
ulu-0.089
J-0.082
ory-0.082
 Jill-0.079
 common-0.075
Tokenowers
Token ID3618
Feature activation-2.61e+00

Pos logit contributions
zed+0.148
oved+0.129
opes+0.122
erved+0.118
iously+0.118
Neg logit contributions
ulu-0.224
ory-0.211
J-0.200
ola-0.195
ora-0.195
Token were
Token ID547
Feature activation-8.46e-01

Pos logit contributions
oved+0.105
zed+0.103
opes+0.102
ths+0.097
iously+0.096
Neg logit contributions
ulu-0.070
ory-0.066
J-0.065
 common-0.061
 Jill-0.060
Token alive
Token ID6776
Feature activation-1.20e+00

Pos logit contributions
oved+0.031
zed+0.030
opes+0.030
ths+0.028
iously+0.028
Neg logit contributions
ulu-0.026
J-0.025
ory-0.025
 common-0.023
 Jill-0.023
Token.
Token ID13
Feature activation-2.46e-01

Pos logit contributions
oved+0.049
zed+0.049
opes+0.048
ths+0.046
iously+0.045
Neg logit contributions
ulu-0.030
J-0.029
ory-0.029
 Jill-0.027
 common-0.026
Token She
Token ID1375
Feature activation-3.82e-01

Pos logit contributions
oved+0.007
zed+0.006
opes+0.006
sed+0.006
iously+0.005
Neg logit contributions
ulu-0.010
ory-0.010
J-0.009
 common-0.009
ola-0.009
Token but
Token ID475
Feature activation-6.99e-01

Pos logit contributions
ulu+0.004
J+0.004
ory+0.004
 common+0.003
 Jill+0.003
Neg logit contributions
oved-0.004
zed-0.004
opes-0.004
ths-0.004
iously-0.004
Token he
Token ID339
Feature activation-1.07e+00

Pos logit contributions
zed+0.023
ths+0.022
oved+0.022
opes+0.022
iously+0.020
Neg logit contributions
ulu-0.024
ory-0.023
J-0.022
ora-0.021
Col-0.020
Token didn
Token ID1422
Feature activation-1.07e+00

Pos logit contributions
oved+0.033
zed+0.032
opes+0.031
ths+0.030
sed+0.029
Neg logit contributions
ulu-0.038
ory-0.037
J-0.037
 common-0.035
 Jill-0.034
Tokenâ
Token ID22940
Feature activation-1.17e+00

Pos logit contributions
oved+0.028
zed+0.027
opes+0.025
ths+0.023
iously+0.023
Neg logit contributions
ulu-0.044
ory-0.044
J-0.043
 common-0.040
 Jill-0.040
Token
Token ID26391
Feature activation-1.93e+00

Pos logit contributions
oved+0.036
zed+0.034
opes+0.032
ths+0.030
iously+0.030
Neg logit contributions
ulu-0.044
ory-0.043
J-0.042
 Jill-0.040
 common-0.040
Token
Token ID8151
Feature activation-5.27e+00

Pos logit contributions
oved+0.051
iously+0.050
zed+0.048
opes+0.047
ths+0.047
Neg logit contributions
J-0.079
 Jill-0.071
ulu-0.070
ory-0.069
 Jenny-0.067
Tokent
Token ID83
Feature activation+7.10e-02

Pos logit contributions
oved+0.156
zed+0.145
opes+0.136
iously+0.128
ths+0.126
Neg logit contributions
ulu-0.195
ory-0.192
J-0.189
 common-0.187
 Jill-0.179
Token know
Token ID760
Feature activation-5.96e-02

Pos logit contributions
ory+0.002
 coral+0.002
ulu+0.002
 mer+0.002
maid+0.002
Neg logit contributions
zed-0.002
 about-0.002
oved-0.002
ending-0.002
aged-0.002
Token which
Token ID543
Feature activation+2.14e-01

Pos logit contributions
oved+0.002
zed+0.002
opes+0.002
ths+0.002
iously+0.002
Neg logit contributions
ulu-0.002
J-0.002
ory-0.002
 Jill-0.002
 common-0.002
Token way
Token ID835
Feature activation+5.95e-01

Pos logit contributions
ory+0.007
J+0.007
ulu+0.007
ola+0.006
ora+0.006
Neg logit contributions
oved-0.008
zed-0.007
opes-0.007
sed-0.007
ths-0.007
Token to
Token ID284
Feature activation+2.39e-01

Pos logit contributions
J+0.020
ulu+0.020
ory+0.020
Col+0.018
 common+0.018
Neg logit contributions
zed-0.019
oved-0.019
opes-0.018
iously-0.017
ths-0.017
Token restless
Token ID42537
Feature activation-2.23e+00

Pos logit contributions
opes+0.040
oved+0.039
 meanings+0.037
iously+0.037
sed+0.036
Neg logit contributions
ulu-0.031
J-0.028
ory-0.027
 Jill-0.027
 Jenny-0.026
Token and
Token ID290
Feature activation-6.87e-01

Pos logit contributions
oved+0.093
opes+0.093
zed+0.092
sed+0.086
ths+0.086
Neg logit contributions
ulu-0.053
ory-0.053
J-0.051
 Jill-0.050
 Jenny-0.046
Token couldn
Token ID3521
Feature activation-2.58e+00

Pos logit contributions
oved+0.024
zed+0.023
opes+0.023
ths+0.022
iously+0.022
Neg logit contributions
ulu-0.022
J-0.021
ory-0.021
 common-0.020
 Jill-0.019
Tokenâ
Token ID22940
Feature activation-1.09e+00

Pos logit contributions
oved+0.087
opes+0.085
sed+0.080
iously+0.079
zed+0.078
Neg logit contributions
ulu-0.086
J-0.082
 common-0.078
 Jill-0.078
ory-0.077
Token
Token ID26391
Feature activation-2.90e+00

Pos logit contributions
oved+0.034
zed+0.033
opes+0.033
ths+0.030
iously+0.030
Neg logit contributions
ulu-0.039
J-0.038
ory-0.038
 common-0.035
 Jill-0.035
Token
Token ID8151
Feature activation-5.25e+00

Pos logit contributions
iously+0.080
sed+0.080
oved+0.080
 meanings+0.078
der+0.077
Neg logit contributions
J-0.099
ory-0.090
 common-0.089
ulu-0.087
 Jenny-0.085
Tokent
Token ID83
Feature activation+2.69e-01

Pos logit contributions
oved+0.171
zed+0.164
opes+0.161
ths+0.151
iously+0.150
Neg logit contributions
ulu-0.181
J-0.176
ory-0.176
 common-0.164
 Jill-0.163
Token get
Token ID651
Feature activation+2.80e-01

Pos logit contributions
ulu+0.008
J+0.008
ory+0.008
 common+0.007
 Jill+0.007
Neg logit contributions
oved-0.010
zed-0.010
opes-0.009
iously-0.009
ths-0.009
Token to
Token ID284
Feature activation-8.37e-01

Pos logit contributions
J+0.009
ulu+0.009
ory+0.009
 common+0.008
ora+0.008
Neg logit contributions
zed-0.009
oved-0.009
ths-0.008
iously-0.008
aged-0.008
Token sleep
Token ID3993
Feature activation-2.29e-01

Pos logit contributions
zed+0.032
oved+0.031
opes+0.030
iously+0.029
ths+0.028
Neg logit contributions
ulu-0.024
J-0.024
ory-0.024
 common-0.021
 Jill-0.021
Token.
Token ID13
Feature activation-5.65e-01

Pos logit contributions
oved+0.010
opes+0.010
zed+0.009
ths+0.009
sed+0.009
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 common-0.005
 Jill-0.005
Token realised
Token ID19169
Feature activation-1.01e+00

Pos logit contributions
oved+0.026
opes+0.025
zed+0.025
ths+0.023
iously+0.023
Neg logit contributions
ulu-0.023
J-0.022
ory-0.022
 Jill-0.020
 common-0.020
Token he
Token ID339
Feature activation-1.38e+00

Pos logit contributions
oved+0.023
zed+0.022
opes+0.021
ths+0.020
iously+0.019
Neg logit contributions
ulu-0.045
ory-0.044
J-0.044
 common-0.041
 Jill-0.041
Token wasn
Token ID2492
Feature activation-1.36e+00

Pos logit contributions
oved+0.054
opes+0.053
zed+0.052
ths+0.049
iously+0.049
Neg logit contributions
ulu-0.038
ory-0.037
J-0.037
 Jill-0.034
 common-0.033
Tokenâ
Token ID22940
Feature activation-1.39e+00

Pos logit contributions
oved+0.040
zed+0.038
opes+0.038
ths+0.035
iously+0.035
Neg logit contributions
ulu-0.052
J-0.050
ory-0.050
 common-0.047
 Jill-0.047
Token
Token ID26391
Feature activation-2.65e+00

Pos logit contributions
oved+0.051
zed+0.049
opes+0.045
iously+0.044
ths+0.043
Neg logit contributions
ulu-0.044
J-0.042
ory-0.042
 Jill-0.039
 common-0.039
Token
Token ID8151
Feature activation-5.22e+00

Pos logit contributions
opes+0.076
oved+0.076
iously+0.075
 meanings+0.070
zed+0.070
Neg logit contributions
J-0.102
ory-0.090
 Jill-0.090
ulu-0.089
 Jenny-0.085
Tokent
Token ID83
Feature activation-3.98e-02

Pos logit contributions
oved+0.173
opes+0.168
zed+0.167
ths+0.156
iously+0.154
Neg logit contributions
ulu-0.178
J-0.172
ory-0.172
 Jill-0.158
 common-0.157
Token scared
Token ID12008
Feature activation-1.52e+00

Pos logit contributions
oved+0.001
zed+0.001
opes+0.001
ths+0.001
iously+0.001
Neg logit contributions
ulu-0.001
J-0.001
ory-0.001
 common-0.001
 Jill-0.001
Token to
Token ID284
Feature activation-3.98e-01

Pos logit contributions
oved+0.048
zed+0.046
opes+0.046
ths+0.042
iously+0.042
Neg logit contributions
ulu-0.055
ory-0.053
J-0.053
 Jill-0.050
 common-0.049
Token go
Token ID467
Feature activation+8.10e-02

Pos logit contributions
oved+0.015
zed+0.014
opes+0.014
iously+0.013
ths+0.013
Neg logit contributions
ulu-0.012
J-0.012
ory-0.011
 common-0.010
 Jill-0.010
Token to
Token ID284
Feature activation-5.67e-01

Pos logit contributions
J+0.003
ory+0.003
ulu+0.003
 common+0.003
Col+0.003
Neg logit contributions
oved-0.002
zed-0.002
ths-0.002
iously-0.002
erved-0.002
Token,
Token ID11
Feature activation-1.11e+00

Pos logit contributions
oved+0.052
zed+0.051
opes+0.050
ths+0.048
iously+0.047
Neg logit contributions
ulu-0.040
J-0.039
ory-0.039
 common-0.035
 Jill-0.035
Token Mike
Token ID4995
Feature activation+8.45e-01

Pos logit contributions
oved+0.039
zed+0.038
ths+0.035
opes+0.035
iously+0.034
Neg logit contributions
ulu-0.035
J-0.034
ory-0.033
 common-0.031
ora-0.029
Token and
Token ID290
Feature activation-1.80e+00

Pos logit contributions
ulu+0.024
ory+0.023
J+0.023
 Jill+0.021
 common+0.020
Neg logit contributions
oved-0.032
opes-0.031
zed-0.031
ths-0.030
sed-0.030
Token his
Token ID465
Feature activation-2.24e+00

Pos logit contributions
zed+0.069
oved+0.064
aged+0.060
iously+0.059
ths+0.058
Neg logit contributions
ory-0.053
ulu-0.050
J-0.048
 common-0.043
ackers-0.043
Token m
Token ID285
Feature activation-4.48e+00

Pos logit contributions
oved+0.093
zed+0.092
opes+0.090
iously+0.085
ths+0.084
Neg logit contributions
ulu-0.059
ory-0.055
J-0.055
 Jill-0.049
 common-0.049
Tokenitten
Token ID2621
Feature activation-5.19e+00

Pos logit contributions
zed+0.124
opes+0.114
oved+0.114
storms+0.105
sed+0.105
Neg logit contributions
ulu-0.173
ory-0.160
J-0.157
ola-0.148
ora-0.140
Token were
Token ID547
Feature activation-1.41e+00

Pos logit contributions
oved+0.203
opes+0.197
iously+0.189
zed+0.188
ths+0.183
Neg logit contributions
ulu-0.137
ory-0.119
J-0.113
 water-0.110
 Jill-0.110
Token insepar
Token ID50140
Feature activation-2.43e+00

Pos logit contributions
oved+0.048
opes+0.046
zed+0.046
iously+0.044
sed+0.043
Neg logit contributions
ulu-0.047
J-0.045
ory-0.044
 Jill-0.042
 common-0.042
Tokenable
Token ID540
Feature activation-1.81e+00

Pos logit contributions
oved+0.098
zed+0.092
ths+0.086
chair+0.085
ending+0.084
Neg logit contributions
ulu-0.065
J-0.060
 common-0.056
ory-0.056
 Jill-0.055
Token.
Token ID13
Feature activation-9.37e-01

Pos logit contributions
zed+0.082
oved+0.080
opes+0.078
ths+0.075
erved+0.074
Neg logit contributions
ory-0.039
ulu-0.038
J-0.035
 Jill-0.034
 Jenny-0.031
Token They
Token ID1119
Feature activation-1.07e+00

Pos logit contributions
oved+0.033
zed+0.032
opes+0.031
iously+0.029
ths+0.029
Neg logit contributions
ulu-0.030
ory-0.029
J-0.029
 common-0.026
 Jill-0.025
Token,
Token ID11
Feature activation-8.90e-01

Pos logit contributions
oved+0.045
zed+0.044
opes+0.042
ths+0.041
iously+0.040
Neg logit contributions
ulu-0.037
J-0.036
ory-0.035
 common-0.033
 Jill-0.032
Token Molly
Token ID30236
Feature activation-8.50e-01

Pos logit contributions
zed+0.038
oved+0.037
ths+0.035
iously+0.034
opes+0.033
Neg logit contributions
J-0.020
ulu-0.020
ory-0.019
 common-0.019
Ar-0.016
Token and
Token ID290
Feature activation-1.88e+00

Pos logit contributions
oved+0.031
opes+0.031
zed+0.029
iously+0.029
sed+0.029
Neg logit contributions
ory-0.024
ulu-0.024
J-0.023
 Jill-0.022
 common-0.021
Token her
Token ID607
Feature activation-2.43e+00

Pos logit contributions
oved+0.076
zed+0.075
opes+0.073
ths+0.070
iously+0.069
Neg logit contributions
ulu-0.051
J-0.049
ory-0.049
 common-0.044
 Jill-0.043
Token m
Token ID285
Feature activation-5.03e+00

Pos logit contributions
oved+0.107
zed+0.104
opes+0.102
iously+0.097
ths+0.097
Neg logit contributions
ulu-0.056
J-0.054
ory-0.054
 Jill-0.049
 common-0.047
Tokenule
Token ID2261
Feature activation-5.16e+00

Pos logit contributions
zed+0.139
oved+0.131
opes+0.125
sed+0.122
ths+0.116
Neg logit contributions
ulu-0.184
ory-0.184
J-0.174
ola-0.161
ora-0.157
Token were
Token ID547
Feature activation-1.96e+00

Pos logit contributions
oved+0.189
iously+0.184
opes+0.182
zed+0.178
sed+0.174
Neg logit contributions
ulu-0.145
ory-0.138
J-0.137
 Jill-0.131
ola-0.123
Token the
Token ID262
Feature activation-1.79e+00

Pos logit contributions
oved+0.078
opes+0.077
sed+0.076
iously+0.074
zed+0.072
Neg logit contributions
ulu-0.054
J-0.052
 Jill-0.049
ory-0.049
 common-0.046
Token best
Token ID1266
Feature activation-8.60e-01

Pos logit contributions
oved+0.050
zed+0.047
opes+0.046
ths+0.044
iously+0.043
Neg logit contributions
ulu-0.071
J-0.069
ory-0.069
 Jill-0.065
 common-0.065
Token of
Token ID286
Feature activation-1.60e+00

Pos logit contributions
opes+0.036
oved+0.036
zed+0.036
sed+0.034
iously+0.034
Neg logit contributions
ulu-0.022
ory-0.021
J-0.020
 Jill-0.019
ola-0.018
Token friends
Token ID2460
Feature activation-1.83e+00

Pos logit contributions
oved+0.064
zed+0.062
opes+0.061
iously+0.058
ths+0.057
Neg logit contributions
ulu-0.045
J-0.042
ory-0.042
 Jill-0.039
 common-0.039
Token They
Token ID1119
Feature activation-7.70e-01

Pos logit contributions
ulu+0.002
J+0.002
ory+0.002
 common+0.002
ola+0.002
Neg logit contributions
oved-0.005
zed-0.004
opes-0.004
sed-0.004
iously-0.004
Token want
Token ID765
Feature activation+1.77e-01

Pos logit contributions
oved+0.028
opes+0.027
zed+0.027
sed+0.024
ths+0.024
Neg logit contributions
ulu-0.023
ory-0.023
J-0.022
 common-0.021
 Jill-0.020
Token to
Token ID284
Feature activation-1.78e-01

Pos logit contributions
ulu+0.008
ory+0.007
J+0.007
 common+0.007
ola+0.007
Neg logit contributions
oved-0.004
opes-0.004
zed-0.004
ths-0.004
iously-0.004
Token make
Token ID787
Feature activation-8.83e-01

Pos logit contributions
oved+0.006
zed+0.006
opes+0.006
ze+0.006
ths+0.006
Neg logit contributions
ory-0.005
ulu-0.005
J-0.005
ora-0.004
ola-0.004
Token snow
Token ID6729
Feature activation-1.56e+00

Pos logit contributions
oved+0.031
opes+0.031
zed+0.030
ths+0.029
iously+0.028
Neg logit contributions
ulu-0.028
ory-0.027
J-0.026
 common-0.024
ola-0.023
Tokenfl
Token ID2704
Feature activation-5.15e+00

Pos logit contributions
oved+0.054
zed+0.052
opes+0.052
ths+0.049
iously+0.048
Neg logit contributions
ulu-0.050
J-0.049
ory-0.048
 Jill-0.045
 common-0.045
Tokenakes
Token ID1124
Feature activation-2.21e+00

Pos logit contributions
zed+0.158
iously+0.145
oved+0.142
sed+0.142
opes+0.134
Neg logit contributions
ulu-0.192
J-0.178
ory-0.173
ola-0.173
 Jill-0.167
Token for
Token ID329
Feature activation-1.58e+00

Pos logit contributions
oved+0.078
zed+0.076
opes+0.074
ths+0.070
iously+0.069
Neg logit contributions
J-0.069
ory-0.069
ulu-0.068
 common-0.062
 Jill-0.059
Token the
Token ID262
Feature activation-2.71e-01

Pos logit contributions
oved+0.060
zed+0.058
opes+0.058
ths+0.055
iously+0.054
Neg logit contributions
ulu-0.047
ory-0.045
J-0.045
 common-0.041
 Jill-0.041
Token window
Token ID4324
Feature activation-5.68e-01

Pos logit contributions
oved+0.010
opes+0.010
zed+0.010
ths+0.009
iously+0.009
Neg logit contributions
ulu-0.008
J-0.008
ory-0.008
 common-0.007
 Jill-0.007
Token.
Token ID13
Feature activation+4.65e-01

Pos logit contributions
oved+0.023
zed+0.022
opes+0.022
ths+0.020
iously+0.020
Neg logit contributions
ulu-0.016
J-0.015
ory-0.015
 common-0.014
 Jill-0.014
Token was
Token ID373
Feature activation-1.49e+00

Pos logit contributions
oved+0.065
opes+0.064
zed+0.062
iously+0.060
sed+0.059
Neg logit contributions
ulu-0.047
J-0.044
ory-0.043
 Jill-0.042
 common-0.039
Token their
Token ID511
Feature activation-2.41e+00

Pos logit contributions
oved+0.056
opes+0.054
zed+0.053
iously+0.051
sed+0.050
Neg logit contributions
ulu-0.045
J-0.043
ory-0.042
 Jill-0.040
 common-0.040
Token son
Token ID3367
Feature activation-2.36e+00

Pos logit contributions
oved+0.088
zed+0.087
opes+0.087
iously+0.079
ths+0.079
Neg logit contributions
ulu-0.072
ory-0.071
J-0.070
 common-0.067
 Jill-0.066
Tokenâ
Token ID22940
Feature activation-8.77e-01

Pos logit contributions
oved+0.092
opes+0.091
zed+0.090
ths+0.084
iously+0.084
Neg logit contributions
ulu-0.065
ory-0.063
J-0.062
 Jill-0.058
 common-0.057
Token
Token ID26391
Feature activation-2.31e+00

Pos logit contributions
oved+0.027
zed+0.026
opes+0.025
ths+0.024
iously+0.024
Neg logit contributions
ulu-0.032
J-0.031
ory-0.031
 Jill-0.029
 common-0.029
Token
Token ID8151
Feature activation-5.15e+00

Pos logit contributions
iously+0.093
oved+0.090
opes+0.087
sed+0.086
der+0.085
Neg logit contributions
J-0.066
 Jill-0.056
ory-0.054
ulu-0.053
 Jenny-0.052
Tokens
Token ID82
Feature activation-1.53e+00

Pos logit contributions
oved+0.195
opes+0.191
zed+0.189
ths+0.180
iously+0.179
Neg logit contributions
ulu-0.150
J-0.145
ory-0.144
 Jill-0.131
 common-0.128
Token special
Token ID2041
Feature activation-3.25e-01

Pos logit contributions
opes+0.062
zed+0.061
oved+0.061
ths+0.057
iously+0.057
Neg logit contributions
ulu-0.038
 Jill-0.036
J-0.036
ory-0.036
 common-0.035
Token place
Token ID1295
Feature activation+6.13e-01

Pos logit contributions
oved+0.013
zed+0.013
opes+0.013
iously+0.012
ths+0.012
Neg logit contributions
ulu-0.008
J-0.008
ory-0.008
 Jill-0.008
 common-0.008
Token.
Token ID13
Feature activation-6.14e-01

Pos logit contributions
ulu+0.019
J+0.019
ory+0.019
 common+0.017
 Jill+0.017
Neg logit contributions
oved-0.022
zed-0.021
opes-0.021
ths-0.019
iously-0.019
Token<|endoftext|>
Token ID50256
Feature activation-5.38e-01

Pos logit contributions
oved+0.023
zed+0.023
opes+0.022
ths+0.021
iously+0.020
Neg logit contributions
ulu-0.018
J-0.017
ory-0.017
 common-0.016
ora-0.015
Token to
Token ID284
Feature activation-1.80e+00

Pos logit contributions
oved+0.037
opes+0.035
sed+0.033
iously+0.033
ths+0.033
Neg logit contributions
ulu-0.031
J-0.029
ory-0.029
 Jill-0.028
 common-0.028
Token send
Token ID3758
Feature activation+5.97e-01

Pos logit contributions
oved+0.070
zed+0.069
opes+0.067
ths+0.064
iously+0.063
Neg logit contributions
ulu-0.051
J-0.049
ory-0.049
 Jill-0.045
 common-0.044
Token soft
Token ID2705
Feature activation-8.42e-01

Pos logit contributions
ulu+0.019
ory+0.018
J+0.018
ola+0.016
 common+0.016
Neg logit contributions
oved-0.021
zed-0.020
opes-0.020
iously-0.019
ths-0.019
Token white
Token ID2330
Feature activation-1.05e+00

Pos logit contributions
oved+0.029
zed+0.028
opes+0.028
iously+0.026
ths+0.026
Neg logit contributions
ulu-0.028
J-0.027
ory-0.027
 Jill-0.025
 common-0.025
Token snow
Token ID6729
Feature activation-1.73e+00

Pos logit contributions
oved+0.037
zed+0.035
opes+0.035
ths+0.033
iously+0.033
Neg logit contributions
ulu-0.034
J-0.033
ory-0.033
 common-0.031
 Jill-0.030
Tokenfl
Token ID2704
Feature activation-5.14e+00

Pos logit contributions
oved+0.057
zed+0.055
opes+0.054
ths+0.051
iously+0.050
Neg logit contributions
ulu-0.058
ory-0.056
J-0.055
 Jill-0.052
 common-0.051
Tokenakes
Token ID1124
Feature activation-2.39e+00

Pos logit contributions
zed+0.137
oved+0.121
sed+0.116
opes+0.114
iously+0.110
Neg logit contributions
ulu-0.206
ory-0.201
J-0.188
ola-0.183
 Jill-0.182
Token into
Token ID656
Feature activation-1.81e+00

Pos logit contributions
oved+0.082
zed+0.079
opes+0.077
iously+0.073
ths+0.073
Neg logit contributions
ulu-0.078
J-0.077
ory-0.076
 common-0.070
 Jill-0.070
Token the
Token ID262
Feature activation-4.40e-01

Pos logit contributions
oved+0.069
zed+0.068
opes+0.067
ths+0.063
iously+0.062
Neg logit contributions
ory-0.052
ulu-0.050
J-0.049
 common-0.043
ora-0.043
Token sky
Token ID6766
Feature activation+1.53e+00

Pos logit contributions
oved+0.016
zed+0.015
opes+0.015
ths+0.014
iously+0.014
Neg logit contributions
ulu-0.014
J-0.013
ory-0.013
 common-0.012
 Jill-0.012
Token.
Token ID13
Feature activation-1.31e+00

Pos logit contributions
ulu+0.040
J+0.039
ory+0.039
 Jill+0.035
 common+0.035
Neg logit contributions
oved-0.062
zed-0.060
opes-0.060
ths-0.057
iously-0.056
Token bear
Token ID6842
Feature activation-5.99e-01

Pos logit contributions
ulu+0.002
J+0.002
ory+0.002
 Jill+0.002
 common+0.002
Neg logit contributions
oved-0.003
opes-0.003
zed-0.003
ths-0.002
iously-0.002
Token and
Token ID290
Feature activation+1.98e-01

Pos logit contributions
oved+0.025
zed+0.024
opes+0.024
ths+0.024
sed+0.023
Neg logit contributions
ulu-0.015
ory-0.014
J-0.013
 Jill-0.013
 common-0.012
Token didn
Token ID1422
Feature activation-1.32e+00

Pos logit contributions
ulu+0.007
ory+0.006
J+0.006
 Jill+0.006
 common+0.006
Neg logit contributions
oved-0.007
opes-0.006
zed-0.006
ths-0.006
iously-0.006
Tokenâ
Token ID22940
Feature activation-8.67e-01

Pos logit contributions
oved+0.042
opes+0.041
zed+0.040
iously+0.038
ths+0.038
Neg logit contributions
ulu-0.047
J-0.045
ory-0.043
 common-0.042
 Jill-0.041
Token
Token ID26391
Feature activation-1.72e+00

Pos logit contributions
oved+0.026
zed+0.025
opes+0.024
iously+0.022
ths+0.022
Neg logit contributions
ulu-0.032
ory-0.031
J-0.031
 Jill-0.029
 common-0.029
Token
Token ID8151
Feature activation-5.13e+00

Pos logit contributions
iously+0.048
oved+0.048
ths+0.046
der+0.044
zed+0.044
Neg logit contributions
J-0.062
ulu-0.055
 Jill-0.053
ory-0.053
 common-0.053
Tokent
Token ID83
Feature activation-4.09e-01

Pos logit contributions
oved+0.160
zed+0.152
opes+0.148
iously+0.137
ths+0.137
Neg logit contributions
ulu-0.182
ory-0.179
J-0.178
 common-0.170
 Jill-0.165
Token want
Token ID765
Feature activation+5.55e-01

Pos logit contributions
oved+0.015
zed+0.014
opes+0.014
erved+0.013
ending+0.012
Neg logit contributions
ory-0.013
ulu-0.012
J-0.012
ola-0.011
 Jill-0.011
Token to
Token ID284
Feature activation-6.06e-01

Pos logit contributions
ulu+0.019
J+0.019
ory+0.019
 Jill+0.018
 common+0.018
Neg logit contributions
oved-0.018
opes-0.017
zed-0.017
ths-0.016
iously-0.016
Token go
Token ID467
Feature activation-8.82e-02

Pos logit contributions
oved+0.022
zed+0.022
opes+0.021
iously+0.020
ths+0.020
Neg logit contributions
ulu-0.018
J-0.018
ory-0.018
 Jill-0.016
ola-0.016
Token anywhere
Token ID6609
Feature activation-1.46e-01

Pos logit contributions
oved+0.002
zed+0.002
erved+0.002
opes+0.002
iously+0.002
Neg logit contributions
J-0.004
ory-0.004
ulu-0.004
ola-0.003
Col-0.003
Token and
Token ID290
Feature activation+7.06e-01

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token they
Token ID484
Feature activation-9.10e-01

Pos logit contributions
ulu+0.021
J+0.020
ory+0.020
 common+0.018
ola+0.018
Neg logit contributions
oved-0.027
zed-0.026
opes-0.026
ths-0.024
iously-0.024
Token played
Token ID2826
Feature activation+6.40e-01

Pos logit contributions
oved+0.032
zed+0.031
opes+0.031
iously+0.029
ths+0.029
Neg logit contributions
ulu-0.029
ory-0.028
J-0.028
 Jill-0.026
 common-0.026
Token make
Token ID787
Feature activation-7.40e-01

Pos logit contributions
ulu+0.019
ory+0.018
J+0.018
 common+0.016
 Jill+0.016
Neg logit contributions
oved-0.024
zed-0.024
opes-0.023
ths-0.022
iously-0.022
Token-
Token ID12
Feature activation-2.19e+00

Pos logit contributions
oved+0.025
zed+0.025
opes+0.024
ths+0.022
iously+0.022
Neg logit contributions
ulu-0.025
ory-0.024
J-0.023
 common-0.022
ora-0.021
Tokenbel
Token ID6667
Feature activation-5.13e+00

Pos logit contributions
oved+0.050
zed+0.047
opes+0.045
ths+0.041
iously+0.040
Neg logit contributions
ulu-0.096
ory-0.095
J-0.093
 common-0.090
 Jill-0.089
Tokenieve
Token ID12311
Feature activation+1.13e+00

Pos logit contributions
sed+0.175
iously+0.159
opes+0.158
oved+0.158
zed+0.148
Neg logit contributions
J-0.178
ulu-0.162
 common-0.159
ola-0.154
 Jill-0.149
Token.
Token ID13
Feature activation-7.07e-01

Pos logit contributions
ulu+0.033
ory+0.032
J+0.031
 common+0.028
 Jill+0.028
Neg logit contributions
oved-0.044
zed-0.042
opes-0.041
ths-0.039
iously-0.039
Token Finally
Token ID9461
Feature activation-5.42e-01

Pos logit contributions
oved+0.033
zed+0.033
opes+0.032
iously+0.030
ths+0.030
Neg logit contributions
ulu-0.014
J-0.013
ory-0.013
 common-0.012
 Jill-0.011
Token,
Token ID11
Feature activation-1.38e+00

Pos logit contributions
zed+0.016
oved+0.014
ths+0.013
iously+0.012
opes+0.012
Neg logit contributions
ulu-0.021
ory-0.020
J-0.019
 common-0.019
rust-0.018
Token they
Token ID484
Feature activation-1.39e+00

Pos logit contributions
zed+0.050
oved+0.046
ths+0.043
opes+0.042
erved+0.042
Neg logit contributions
ulu-0.043
J-0.037
ory-0.036
 common-0.036
ola-0.034
Token excited
Token ID6568
Feature activation-1.35e+00

Pos logit contributions
oved+0.021
zed+0.020
opes+0.020
iously+0.020
ths+0.019
Neg logit contributions
ulu-0.017
J-0.016
 Jill-0.016
ory-0.015
 Jenny-0.015
Token and
Token ID290
Feature activation-8.41e-02

Pos logit contributions
zed+0.052
oved+0.052
opes+0.050
sed+0.047
ths+0.047
Neg logit contributions
ory-0.038
 Jill-0.038
J-0.037
ulu-0.037
 Jenny-0.035
Token couldn
Token ID3521
Feature activation-2.14e+00

Pos logit contributions
oved+0.003
zed+0.003
opes+0.003
ths+0.002
iously+0.002
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 Jill-0.003
 common-0.003
Tokenâ
Token ID22940
Feature activation-9.05e-01

Pos logit contributions
oved+0.065
opes+0.063
zed+0.061
iously+0.059
ths+0.058
Neg logit contributions
ulu-0.079
J-0.076
ory-0.074
 Jill-0.072
 common-0.071
Token
Token ID26391
Feature activation-2.27e+00

Pos logit contributions
oved+0.029
zed+0.028
opes+0.026
ths+0.025
iously+0.025
Neg logit contributions
ulu-0.033
ory-0.031
J-0.031
 Jill-0.029
 common-0.029
Token
Token ID8151
Feature activation-5.12e+00

Pos logit contributions
oved+0.073
iously+0.072
opes+0.070
ths+0.069
zed+0.068
Neg logit contributions
J-0.078
ulu-0.071
 Jill-0.071
ory-0.070
 common-0.070
Tokent
Token ID83
Feature activation+5.58e-01

Pos logit contributions
oved+0.153
zed+0.141
opes+0.134
iously+0.127
ths+0.125
Neg logit contributions
ulu-0.188
ory-0.184
J-0.183
 common-0.179
 Jill-0.172
Token wait
Token ID4043
Feature activation+1.47e+00

Pos logit contributions
ulu+0.019
ory+0.018
J+0.018
 common+0.017
ora+0.016
Neg logit contributions
oved-0.018
zed-0.018
iously-0.016
opes-0.016
ths-0.015
Token to
Token ID284
Feature activation-6.04e-01

Pos logit contributions
ulu+0.043
J+0.043
 Jill+0.041
ory+0.041
 common+0.040
Neg logit contributions
oved-0.056
opes-0.053
zed-0.051
ths-0.050
sed-0.049
Token have
Token ID423
Feature activation+7.73e-01

Pos logit contributions
zed+0.020
oved+0.019
opes+0.019
ths+0.018
erved+0.018
Neg logit contributions
ulu-0.020
ory-0.019
J-0.019
ora-0.016
ola-0.016
Token fun
Token ID1257
Feature activation+1.25e+00

Pos logit contributions
ulu+0.025
ory+0.024
J+0.023
ora+0.022
ola+0.021
Neg logit contributions
zed-0.026
oved-0.026
opes-0.025
ths-0.024
erved-0.023
Token.
Token ID13
Feature activation+3.46e-01

Pos logit contributions
oved+0.121
zed+0.119
opes+0.119
ths+0.114
sed+0.110
Neg logit contributions
ulu-0.083
ory-0.081
J-0.079
 Jill-0.074
 common-0.070
Token Jake
Token ID14757
Feature activation+7.83e-01

Pos logit contributions
ulu+0.010
J+0.010
ory+0.010
 Jill+0.009
 common+0.009
Neg logit contributions
oved-0.013
zed-0.013
opes-0.012
ths-0.012
iously-0.012
Token had
Token ID550
Feature activation+5.15e-01

Pos logit contributions
ory+0.021
ulu+0.020
J+0.020
 Jill+0.019
 Jenny+0.018
Neg logit contributions
oved-0.031
opes-0.030
zed-0.029
ths-0.028
iously-0.027
Token never
Token ID1239
Feature activation+1.19e-01

Pos logit contributions
J+0.016
ulu+0.016
ory+0.015
 Jill+0.015
 common+0.014
Neg logit contributions
oved-0.019
opes-0.018
zed-0.017
ths-0.017
iously-0.017
Token had
Token ID550
Feature activation+3.52e-01

Pos logit contributions
ulu+0.004
J+0.004
ory+0.004
 Jill+0.003
 common+0.003
Neg logit contributions
oved-0.004
opes-0.004
zed-0.004
ths-0.004
iously-0.004
Token por
Token ID16964
Feature activation-5.11e+00

Pos logit contributions
ulu+0.011
J+0.010
ory+0.010
 Jill+0.010
 common+0.009
Neg logit contributions
oved-0.013
opes-0.012
zed-0.012
ths-0.012
iously-0.012
Tokenridge
Token ID12818
Feature activation-4.59e+00

Pos logit contributions
oved+0.113
ths+0.103
opes+0.097
zed+0.095
sed+0.094
Neg logit contributions
ory-0.213
J-0.206
ulu-0.204
 opener-0.194
 Jolly-0.193
Token before
Token ID878
Feature activation-4.31e-01

Pos logit contributions
oved+0.190
opes+0.188
zed+0.184
ths+0.176
sed+0.173
Neg logit contributions
ulu-0.114
ory-0.112
J-0.111
 Jill-0.101
 common-0.097
Token and
Token ID290
Feature activation+7.25e-01

Pos logit contributions
oved+0.018
zed+0.017
opes+0.017
ths+0.016
sed+0.016
Neg logit contributions
ulu-0.011
ory-0.010
J-0.010
 Jill-0.010
 common-0.010
Token he
Token ID339
Feature activation-6.38e-01

Pos logit contributions
ulu+0.018
J+0.017
ory+0.017
 Jill+0.016
 common+0.015
Neg logit contributions
oved-0.031
zed-0.030
opes-0.030
ths-0.028
iously-0.028
Token was
Token ID373
Feature activation+5.24e-03

Pos logit contributions
oved+0.024
opes+0.024
zed+0.023
ths+0.022
iously+0.022
Neg logit contributions
ulu-0.017
ory-0.017
J-0.017
 Jill-0.016
 common-0.015
Token and
Token ID290
Feature activation-6.29e-01

Pos logit contributions
oved+0.007
zed+0.007
opes+0.007
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.006
J-0.006
 common-0.006
ory-0.006
 Jill-0.005
Token Jack
Token ID3619
Feature activation-5.53e-01

Pos logit contributions
iously+0.018
ths+0.018
sed+0.017
zed+0.017
oved+0.017
Neg logit contributions
ulu-0.021
 common-0.020
Ar-0.019
 opener-0.019
J-0.019
Token didn
Token ID1422
Feature activation-1.11e+00

Pos logit contributions
oved+0.021
zed+0.021
opes+0.021
ths+0.019
iously+0.019
Neg logit contributions
ulu-0.016
ory-0.015
J-0.015
 Jill-0.014
ola-0.013
Tokenâ
Token ID22940
Feature activation-1.20e+00

Pos logit contributions
oved+0.035
opes+0.033
zed+0.032
sed+0.031
iously+0.030
Neg logit contributions
ulu-0.040
J-0.039
ory-0.038
 common-0.036
 Jill-0.036
Token
Token ID26391
Feature activation-2.31e+00

Pos logit contributions
oved+0.039
zed+0.037
opes+0.036
ths+0.034
iously+0.034
Neg logit contributions
ulu-0.042
J-0.041
ory-0.041
 common-0.038
 Jill-0.038
Token
Token ID8151
Feature activation-5.08e+00

Pos logit contributions
oved+0.066
opes+0.063
zed+0.061
iously+0.061
ths+0.059
Neg logit contributions
J-0.090
ory-0.086
ulu-0.084
 Jill-0.083
 Jenny-0.079
Tokent
Token ID83
Feature activation-7.27e-02

Pos logit contributions
oved+0.160
zed+0.152
opes+0.147
iously+0.138
ths+0.137
Neg logit contributions
ulu-0.179
J-0.175
ory-0.175
 common-0.166
 Jill-0.163
Token give
Token ID1577
Feature activation+2.26e+00

Pos logit contributions
oved+0.002
zed+0.002
opes+0.002
ze+0.002
ending+0.002
Neg logit contributions
J-0.002
ulu-0.002
ory-0.002
 common-0.002
ora-0.002
Token up
Token ID510
Feature activation-1.03e+00

Pos logit contributions
ulu+0.084
J+0.084
Ar+0.078
 opener+0.078
ory+0.076
Neg logit contributions
zed-0.060
oved-0.057
opes-0.055
ths-0.055
iously-0.053
Token.
Token ID13
Feature activation-8.43e-02

Pos logit contributions
oved+0.037
zed+0.036
opes+0.035
iously+0.034
ths+0.034
Neg logit contributions
ulu-0.032
J-0.030
ory-0.030
 common-0.027
 Jill-0.027
Token They
Token ID1119
Feature activation-1.38e-01

Pos logit contributions
oved+0.003
zed+0.003
opes+0.003
iously+0.002
ths+0.002
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 common-0.003
ora-0.002
Token.
Token ID13
Feature activation-2.30e-01

Pos logit contributions
ulu+0.040
J+0.038
ory+0.037
 Jill+0.034
 common+0.034
Neg logit contributions
oved-0.052
zed-0.049
opes-0.048
iously-0.046
ths-0.045
Token They
Token ID1119
Feature activation-7.80e-01

Pos logit contributions
oved+0.008
zed+0.008
opes+0.008
sed+0.007
ths+0.007
Neg logit contributions
ulu-0.007
ory-0.007
J-0.007
ola-0.006
 Jill-0.006
Token never
Token ID1239
Feature activation-1.01e+00

Pos logit contributions
oved+0.023
zed+0.022
opes+0.022
ths+0.020
iously+0.020
Neg logit contributions
ulu-0.030
J-0.029
ory-0.029
 common-0.027
 Jill-0.027
Token planted
Token ID18969
Feature activation-4.41e-01

Pos logit contributions
oved+0.037
zed+0.036
opes+0.035
ths+0.033
iously+0.033
Neg logit contributions
ulu-0.031
J-0.030
ory-0.030
 common-0.027
 Jill-0.027
Token sun
Token ID4252
Feature activation-1.41e+00

Pos logit contributions
oved+0.017
zed+0.016
opes+0.016
ths+0.015
iously+0.015
Neg logit contributions
ulu-0.013
J-0.013
ory-0.013
ola-0.011
 Jill-0.011
Tokenfl
Token ID2704
Feature activation-5.03e+00

Pos logit contributions
oved+0.058
zed+0.056
opes+0.055
ths+0.052
iously+0.052
Neg logit contributions
ulu-0.037
J-0.035
ory-0.035
 Jill-0.032
 common-0.032
Tokenowers
Token ID3618
Feature activation-2.10e+00

Pos logit contributions
zed+0.136
oved+0.119
opes+0.116
sed+0.110
iously+0.109
Neg logit contributions
ulu-0.213
ory-0.206
J-0.195
ola-0.188
ora-0.187
Token again
Token ID757
Feature activation+6.62e-02

Pos logit contributions
oved+0.077
zed+0.073
opes+0.072
ths+0.068
iously+0.068
Neg logit contributions
ulu-0.064
J-0.064
ory-0.062
 common-0.058
 Jill-0.057
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
ulu+0.002
ory+0.002
J+0.002
 Jill+0.002
 common+0.002
Neg logit contributions
oved-0.003
zed-0.002
opes-0.002
iously-0.002
ths-0.002
Token<|endoftext|>
Token ID50256
Feature activation+6.87e-02

Pos logit contributions
oved+0.021
zed+0.020
opes+0.020
sed+0.019
ths+0.018
Neg logit contributions
ulu-0.017
ory-0.016
J-0.016
ola-0.014
 Jill-0.014
TokenL
Token ID43
Feature activation+1.45e+00

Pos logit contributions
ory+0.003
ulu+0.002
J+0.002
 common+0.002
 Jill+0.002
Neg logit contributions
oved-0.002
zed-0.002
opes-0.002
 ow-0.002
 Leave-0.002
Token onwards
Token ID31719
Feature activation-1.22e+00

Pos logit contributions
opes+0.072
oved+0.072
iously+0.067
sed+0.067
zed+0.066
Neg logit contributions
ulu-0.050
J-0.049
ory-0.046
 Jill-0.043
ola-0.043
Token,
Token ID11
Feature activation-8.90e-01

Pos logit contributions
oved+0.045
zed+0.044
opes+0.042
ths+0.041
iously+0.040
Neg logit contributions
ulu-0.037
J-0.036
ory-0.035
 common-0.033
 Jill-0.032
Token Molly
Token ID30236
Feature activation-8.50e-01

Pos logit contributions
zed+0.038
oved+0.037
ths+0.035
iously+0.034
opes+0.033
Neg logit contributions
J-0.020
ulu-0.020
ory-0.019
 common-0.019
Ar-0.016
Token and
Token ID290
Feature activation-1.88e+00

Pos logit contributions
oved+0.031
opes+0.031
zed+0.029
iously+0.029
sed+0.029
Neg logit contributions
ory-0.024
ulu-0.024
J-0.023
 Jill-0.022
 common-0.021
Token her
Token ID607
Feature activation-2.43e+00

Pos logit contributions
oved+0.076
zed+0.075
opes+0.073
ths+0.070
iously+0.069
Neg logit contributions
ulu-0.051
J-0.049
ory-0.049
 common-0.044
 Jill-0.043
Token m
Token ID285
Feature activation-5.03e+00

Pos logit contributions
oved+0.107
zed+0.104
opes+0.102
iously+0.097
ths+0.097
Neg logit contributions
ulu-0.056
J-0.054
ory-0.054
 Jill-0.049
 common-0.047
Tokenule
Token ID2261
Feature activation-5.16e+00

Pos logit contributions
zed+0.139
oved+0.131
opes+0.125
sed+0.122
ths+0.116
Neg logit contributions
ulu-0.184
ory-0.184
J-0.174
ola-0.161
ora-0.157
Token were
Token ID547
Feature activation-1.96e+00

Pos logit contributions
oved+0.189
iously+0.184
opes+0.182
zed+0.178
sed+0.174
Neg logit contributions
ulu-0.145
ory-0.138
J-0.137
 Jill-0.131
ola-0.123
Token the
Token ID262
Feature activation-1.79e+00

Pos logit contributions
oved+0.078
opes+0.077
sed+0.076
iously+0.074
zed+0.072
Neg logit contributions
ulu-0.054
J-0.052
 Jill-0.049
ory-0.049
 common-0.046
Token best
Token ID1266
Feature activation-8.60e-01

Pos logit contributions
oved+0.050
zed+0.047
opes+0.046
ths+0.044
iously+0.043
Neg logit contributions
ulu-0.071
J-0.069
ory-0.069
 Jill-0.065
 common-0.065
Token of
Token ID286
Feature activation-1.60e+00

Pos logit contributions
opes+0.036
oved+0.036
zed+0.036
sed+0.034
iously+0.034
Neg logit contributions
ulu-0.022
ory-0.021
J-0.020
 Jill-0.019
ola-0.018
Token pen
Token ID3112
Feature activation-1.55e+00

Pos logit contributions
oved+0.043
zed+0.043
opes+0.042
ths+0.040
iously+0.039
Neg logit contributions
ulu-0.046
ory-0.045
 common-0.043
J-0.042
 Jill-0.041
Token and
Token ID290
Feature activation+1.63e-01

Pos logit contributions
opes+0.062
zed+0.062
ths+0.061
oved+0.060
iously+0.060
Neg logit contributions
ulu-0.036
J-0.035
ory-0.035
 common-0.031
 Jill-0.031
Token didn
Token ID1422
Feature activation-1.38e+00

Pos logit contributions
ulu+0.005
J+0.005
 Jill+0.005
ory+0.005
 common+0.005
Neg logit contributions
oved-0.006
opes-0.005
zed-0.005
ths-0.005
iously-0.005
Tokenâ
Token ID22940
Feature activation-1.27e+00

Pos logit contributions
oved+0.041
opes+0.039
zed+0.039
ths+0.037
iously+0.037
Neg logit contributions
ulu-0.052
J-0.050
ory-0.049
 common-0.047
 Jill-0.047
Token
Token ID26391
Feature activation-1.72e+00

Pos logit contributions
oved+0.039
zed+0.038
opes+0.035
ths+0.033
iously+0.033
Neg logit contributions
ulu-0.047
ory-0.046
J-0.045
 Jill-0.042
 common-0.042
Token
Token ID8151
Feature activation-5.02e+00

Pos logit contributions
iously+0.052
der+0.046
oved+0.046
opes+0.046
ths+0.044
Neg logit contributions
J-0.067
ulu-0.055
L-0.055
 Jenny-0.054
 Jill-0.053
Tokent
Token ID83
Feature activation-4.73e-01

Pos logit contributions
oved+0.161
zed+0.155
opes+0.152
ths+0.142
iously+0.141
Neg logit contributions
ulu-0.176
J-0.171
ory-0.170
 common-0.159
 Jill-0.158
Token know
Token ID760
Feature activation-5.17e-01

Pos logit contributions
zed+0.017
oved+0.017
opes+0.015
erved+0.015
aged+0.015
Neg logit contributions
ory-0.015
ulu-0.014
J-0.014
ora-0.013
ola-0.013
Token where
Token ID810
Feature activation+9.64e-02

Pos logit contributions
oved+0.018
zed+0.017
opes+0.017
iously+0.016
ths+0.016
Neg logit contributions
ulu-0.017
J-0.017
ory-0.016
 Jill-0.016
 common-0.015
Token it
Token ID340
Feature activation-1.97e-01

Pos logit contributions
ulu+0.002
J+0.002
ory+0.002
 common+0.002
 Jill+0.002
Neg logit contributions
oved-0.004
zed-0.004
opes-0.004
ths-0.004
iously-0.004
Token was
Token ID373
Feature activation+2.81e-01

Pos logit contributions
oved+0.008
opes+0.008
zed+0.008
iously+0.008
ths+0.008
Neg logit contributions
ulu-0.005
J-0.004
ory-0.004
 Jill-0.004
 common-0.004
Token wealthy
Token ID11574
Feature activation-4.15e-01

Pos logit contributions
oved+0.017
zed+0.017
ths+0.017
opes+0.017
iously+0.016
Neg logit contributions
ulu-0.017
J-0.016
 common-0.016
ory-0.016
 Jill-0.016
Token prince
Token ID19716
Feature activation-6.30e-01

Pos logit contributions
oved+0.016
zed+0.016
opes+0.015
ths+0.015
iously+0.015
Neg logit contributions
ulu-0.012
J-0.011
 common-0.010
 Jill-0.010
ory-0.010
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
oved+0.024
opes+0.023
zed+0.023
iously+0.021
ths+0.021
Neg logit contributions
ulu-0.018
ory-0.018
J-0.018
 Jill-0.016
 common-0.016
Token his
Token ID465
Feature activation-2.06e+00

Pos logit contributions
zed+0.042
oved+0.039
 meanings+0.039
iously+0.038
opes+0.037
Neg logit contributions
ulu-0.039
J-0.039
ory-0.038
ola-0.036
oe-0.035
Token sun
Token ID4252
Feature activation-1.43e+00

Pos logit contributions
oved+0.078
zed+0.076
opes+0.075
ths+0.071
iously+0.071
Neg logit contributions
ulu-0.060
J-0.059
ory-0.058
 common-0.053
 Jill-0.053
Tokenfl
Token ID2704
Feature activation-5.02e+00

Pos logit contributions
oved+0.056
zed+0.054
opes+0.053
iously+0.051
ths+0.050
Neg logit contributions
ulu-0.039
ory-0.037
J-0.036
 Jill-0.033
 common-0.033
Tokenowers
Token ID3618
Feature activation-2.30e+00

Pos logit contributions
zed+0.127
oved+0.117
opes+0.108
iously+0.107
erved+0.104
Neg logit contributions
ulu-0.209
ory-0.206
J-0.190
ora-0.186
ola-0.185
Token lived
Token ID5615
Feature activation+2.01e-01

Pos logit contributions
oved+0.087
zed+0.085
opes+0.084
iously+0.080
erved+0.079
Neg logit contributions
ulu-0.067
ory-0.064
J-0.061
 common-0.058
 Jill-0.057
Token happily
Token ID18177
Feature activation-1.35e+00

Pos logit contributions
ulu+0.007
ory+0.007
J+0.007
 common+0.006
 Jill+0.006
Neg logit contributions
oved-0.007
zed-0.006
opes-0.006
ths-0.006
iously-0.006
Token ever
Token ID1683
Feature activation-7.33e-01

Pos logit contributions
oved+0.051
opes+0.051
zed+0.051
ths+0.047
erved+0.046
Neg logit contributions
ulu-0.038
ory-0.038
J-0.036
 common-0.033
 Jill-0.033
Token after
Token ID706
Feature activation-4.28e-01

Pos logit contributions
oved+0.023
zed+0.022
opes+0.022
iously+0.021
ths+0.021
Neg logit contributions
ulu-0.027
J-0.025
ory-0.024
 Jill-0.023
 common-0.023
Token was
Token ID373
Feature activation-2.55e-01

Pos logit contributions
ulu+0.006
ory+0.006
J+0.006
 Jill+0.006
 common+0.006
Neg logit contributions
oved-0.007
opes-0.007
zed-0.007
ths-0.007
iously-0.007
Token smarter
Token ID23714
Feature activation+4.98e-01

Pos logit contributions
oved+0.009
zed+0.008
opes+0.008
ths+0.008
iously+0.008
Neg logit contributions
ulu-0.009
ory-0.008
J-0.008
 common-0.008
 Jill-0.008
Token.
Token ID13
Feature activation-2.75e-01

Pos logit contributions
ulu+0.013
J+0.013
ory+0.013
 common+0.012
 Jill+0.012
Neg logit contributions
oved-0.020
zed-0.020
opes-0.019
ths-0.018
iously-0.018
Token In
Token ID554
Feature activation+3.48e-01

Pos logit contributions
oved+0.009
zed+0.009
opes+0.009
ths+0.008
iously+0.008
Neg logit contributions
ulu-0.009
J-0.009
ory-0.009
 common-0.008
 Jill-0.008
Token the
Token ID262
Feature activation+3.17e-01

Pos logit contributions
ulu+0.010
ory+0.010
J+0.009
 Jill+0.008
ora+0.008
Neg logit contributions
oved-0.014
zed-0.014
opes-0.013
ths-0.013
iously-0.012
Token end
Token ID886
Feature activation+3.23e+00

Pos logit contributions
ulu+0.010
ory+0.010
J+0.009
emo+0.009
ola+0.009
Neg logit contributions
oved-0.011
zed-0.011
opes-0.010
ths-0.010
erved-0.010
Token,
Token ID11
Feature activation+2.72e-01

Pos logit contributions
ory+0.113
ulu+0.111
J+0.106
 common+0.099
ora+0.098
Neg logit contributions
oved-0.102
zed-0.101
opes-0.096
ths-0.094
iously-0.089
Token he
Token ID339
Feature activation-1.81e-01

Pos logit contributions
ulu+0.008
ory+0.008
J+0.008
 common+0.007
ora+0.007
Neg logit contributions
zed-0.010
oved-0.010
opes-0.010
ths-0.009
iously-0.009
Token said
Token ID531
Feature activation-1.54e-01

Pos logit contributions
oved+0.006
zed+0.006
opes+0.006
ths+0.006
iously+0.005
Neg logit contributions
ulu-0.006
J-0.006
ory-0.006
 common-0.005
 Jill-0.005
Token a
Token ID257
Feature activation+4.30e-01

Pos logit contributions
oved+0.005
opes+0.005
zed+0.005
ths+0.004
iously+0.004
Neg logit contributions
J-0.005
ulu-0.005
ory-0.005
 Jill-0.005
 common-0.005
Token word
Token ID1573
Feature activation+3.10e-01

Pos logit contributions
ulu+0.014
ory+0.014
J+0.013
ola+0.012
 Jill+0.012
Neg logit contributions
oved-0.014
zed-0.014
ths-0.013
opes-0.013
sed-0.013
Token they
Token ID484
Feature activation-4.06e-01

Pos logit contributions
ulu+0.015
ory+0.015
J+0.014
 common+0.014
ora+0.013
Neg logit contributions
zed-0.018
oved-0.018
opes-0.017
ths-0.017
sed-0.016
Token all
Token ID477
Feature activation+3.23e-01

Pos logit contributions
oved+0.013
zed+0.013
opes+0.012
ths+0.011
sed+0.011
Neg logit contributions
ulu-0.014
J-0.014
ory-0.013
 common-0.013
 Jill-0.012
Token had
Token ID550
Feature activation+1.59e-01

Pos logit contributions
ulu+0.010
J+0.010
ory+0.010
 common+0.009
 Jill+0.009
Neg logit contributions
oved-0.011
zed-0.011
opes-0.011
ths-0.010
iously-0.010
Token a
Token ID257
Feature activation-1.66e-01

Pos logit contributions
J+0.004
ulu+0.004
ory+0.004
 Jill+0.004
 common+0.004
Neg logit contributions
oved-0.006
zed-0.006
opes-0.006
iously-0.006
ths-0.006
Token great
Token ID1049
Feature activation+5.19e-01

Pos logit contributions
oved+0.005
zed+0.005
opes+0.005
sed+0.005
ths+0.005
Neg logit contributions
ulu-0.006
J-0.005
ory-0.005
 Jill-0.005
ola-0.005
Token time
Token ID640
Feature activation+3.15e+00

Pos logit contributions
ulu+0.016
J+0.016
ory+0.015
 Jill+0.014
 common+0.014
Neg logit contributions
oved-0.019
zed-0.018
opes-0.018
ths-0.017
iously-0.017
Token playing
Token ID2712
Feature activation+3.48e-01

Pos logit contributions
ulu+0.087
J+0.085
ory+0.084
 Jill+0.079
 common+0.077
Neg logit contributions
oved-0.121
zed-0.119
opes-0.118
ths-0.112
iously-0.111
Token games
Token ID1830
Feature activation+1.28e+00

Pos logit contributions
ulu+0.010
J+0.010
ory+0.010
 common+0.009
 Jill+0.009
Neg logit contributions
oved-0.013
zed-0.013
opes-0.013
ths-0.012
iously-0.012
Token and
Token ID290
Feature activation+5.64e-01

Pos logit contributions
ulu+0.034
J+0.033
ory+0.033
 common+0.030
 Jill+0.030
Neg logit contributions
oved-0.052
zed-0.050
opes-0.050
ths-0.047
iously-0.047
Token eating
Token ID6600
Feature activation-9.40e-01

Pos logit contributions
ory+0.024
ulu+0.024
J+0.023
 common+0.022
ora+0.022
Neg logit contributions
zed-0.014
oved-0.013
opes-0.013
ths-0.012
sed-0.011
Token cake
Token ID12187
Feature activation-2.45e-01

Pos logit contributions
oved+0.030
zed+0.029
opes+0.029
ths+0.026
iously+0.026
Neg logit contributions
ulu-0.033
ory-0.031
J-0.031
ola-0.029
ora-0.028
Token Then
Token ID3244
Feature activation+8.22e-01

Pos logit contributions
ulu+0.007
ory+0.007
J+0.007
 common+0.007
 deeper+0.007
Neg logit contributions
 Leave-0.004
oved-0.004
opes-0.003
zed-0.003
der-0.003
Token give
Token ID1577
Feature activation+2.61e+00

Pos logit contributions
ulu+0.029
J+0.029
ory+0.027
 common+0.025
emo+0.025
Neg logit contributions
zed-0.025
ths-0.023
iously-0.023
oved-0.023
opes-0.022
Token it
Token ID340
Feature activation-3.05e-01

Pos logit contributions
ulu+0.088
 opener+0.083
J+0.081
 common+0.078
ory+0.076
Neg logit contributions
zed-0.084
oved-0.079
iously-0.074
ths-0.074
erved-0.074
Token to
Token ID284
Feature activation-4.39e-01

Pos logit contributions
oved+0.009
zed+0.009
opes+0.009
erved+0.008
iously+0.008
Neg logit contributions
ulu-0.011
J-0.011
ory-0.011
 common-0.010
ola-0.010
Token someone
Token ID2130
Feature activation+1.62e+00

Pos logit contributions
zed+0.017
oved+0.016
opes+0.016
 ow+0.016
iously+0.016
Neg logit contributions
J-0.011
ulu-0.011
ory-0.011
 common-0.010
 opener-0.009
Token you
Token ID345
Feature activation+3.07e+00

Pos logit contributions
ulu+0.061
J+0.060
ory+0.058
 common+0.054
 Jill+0.053
Neg logit contributions
oved-0.049
zed-0.046
opes-0.044
iously-0.042
ths-0.042
Token like
Token ID588
Feature activation+1.91e+00

Pos logit contributions
ulu+0.090
J+0.086
ory+0.084
 common+0.078
 Jill+0.077
Neg logit contributions
oved-0.118
zed-0.113
opes-0.112
iously-0.105
ths-0.105
Token.
Token ID13
Feature activation+7.43e-02

Pos logit contributions
ulu+0.058
J+0.056
ory+0.055
 common+0.051
 Jill+0.050
Neg logit contributions
oved-0.071
zed-0.068
opes-0.068
ths-0.064
iously-0.064
Token They
Token ID1119
Feature activation+1.28e-01

Pos logit contributions
ulu+0.003
ory+0.003
J+0.003
ora+0.003
 deeper+0.003
Neg logit contributions
 Leave-0.002
oved-0.001
opes-0.001
zed-0.001
der-0.001
Token will
Token ID481
Feature activation+3.52e-01

Pos logit contributions
ulu+0.004
J+0.004
ory+0.003
 Jill+0.003
 common+0.003
Neg logit contributions
oved-0.005
opes-0.005
zed-0.005
ths-0.004
iously-0.004
Token be
Token ID307
Feature activation+1.20e+00

Pos logit contributions
ulu+0.011
ory+0.011
J+0.011
 Jill+0.010
ola+0.010
Neg logit contributions
oved-0.013
opes-0.012
zed-0.012
ths-0.011
iously-0.011
Token.
Token ID13
Feature activation+5.51e-01

Pos logit contributions
ulu+0.022
J+0.021
ory+0.020
 Jill+0.019
 common+0.019
Neg logit contributions
oved-0.038
zed-0.038
opes-0.037
ths-0.036
iously-0.035
Token It
Token ID632
Feature activation+1.52e+00

Pos logit contributions
ulu+0.022
ory+0.022
J+0.022
 common+0.020
 Jill+0.020
Neg logit contributions
oved-0.015
zed-0.014
opes-0.014
iously-0.013
ths-0.012
Token says
Token ID1139
Feature activation+1.41e+00

Pos logit contributions
ory+0.056
ulu+0.055
J+0.055
ola+0.048
 Jill+0.048
Neg logit contributions
oved-0.047
opes-0.044
zed-0.044
ths-0.041
sed-0.041
Token,
Token ID11
Feature activation-1.04e-01

Pos logit contributions
ulu+0.048
J+0.047
ory+0.047
 common+0.044
 Jill+0.043
Neg logit contributions
oved-0.047
zed-0.045
opes-0.044
ths-0.041
iously-0.041
Token "
Token ID366
Feature activation-8.45e-01

Pos logit contributions
oved+0.003
zed+0.003
opes+0.003
ths+0.003
iously+0.003
Neg logit contributions
ulu-0.004
J-0.004
ory-0.004
 Jill-0.003
 common-0.003
TokenJoin
Token ID18234
Feature activation+3.43e+00

Pos logit contributions
oved+0.030
zed+0.027
ths+0.027
opes+0.027
ending+0.026
Neg logit contributions
ulu-0.026
ory-0.025
 common-0.023
 Jill-0.023
J-0.022
Token the
Token ID262
Feature activation+1.06e-02

Pos logit contributions
ulu+0.111
ory+0.107
J+0.101
ola+0.090
 Jill+0.089
Neg logit contributions
oved-0.117
opes-0.117
zed-0.113
ths-0.108
 meanings-0.104
Token Jazz
Token ID21406
Feature activation+8.57e-01

Pos logit contributions
ulu+0.000
ory+0.000
J+0.000
ackers+0.000
emo+0.000
Neg logit contributions
oved-0.000
opes-0.000
 meanings-0.000
zed-0.000
sed-0.000
Token Club
Token ID6289
Feature activation+1.84e+00

Pos logit contributions
ulu+0.025
J+0.024
ory+0.024
 Jill+0.022
 common+0.022
Neg logit contributions
oved-0.032
zed-0.031
opes-0.031
ths-0.029
iously-0.029
Token!
Token ID0
Feature activation-8.06e-01

Pos logit contributions
ulu+0.059
J+0.057
ory+0.057
 common+0.052
 Jill+0.050
Neg logit contributions
oved-0.065
opes-0.060
zed-0.060
ths-0.056
iously-0.056
Token Learn
Token ID14365
Feature activation+1.58e+00

Pos logit contributions
oved+0.018
 Leave+0.018
opes+0.016
zed+0.016
chair+0.015
Neg logit contributions
ulu-0.035
ory-0.034
 common-0.032
J-0.032
ackers-0.030
Token!"
Token ID2474
Feature activation+4.62e-01

Pos logit contributions
ulu+0.013
ory+0.011
J+0.011
 Jill+0.011
ola+0.011
Neg logit contributions
oved-0.019
opes-0.019
zed-0.019
ths-0.018
sed-0.018
Token He
Token ID679
Feature activation+2.49e-01

Pos logit contributions
ulu+0.014
ory+0.013
J+0.013
 common+0.013
ola+0.011
Neg logit contributions
oved-0.017
zed-0.017
opes-0.016
iously-0.016
ths-0.015
Token jumped
Token ID11687
Feature activation+1.49e-01

Pos logit contributions
ulu+0.007
J+0.007
ory+0.007
 common+0.007
 Jill+0.006
Neg logit contributions
oved-0.009
zed-0.009
opes-0.009
ths-0.008
iously-0.008
Token into
Token ID656
Feature activation-2.48e-01

Pos logit contributions
ulu+0.006
J+0.005
 common+0.005
ory+0.005
ola+0.005
Neg logit contributions
oved-0.004
zed-0.004
iously-0.004
opes-0.004
ze-0.004
Token the
Token ID262
Feature activation+9.84e-01

Pos logit contributions
zed+0.007
iously+0.007
 ow+0.006
opes+0.006
oved+0.006
Neg logit contributions
ory-0.009
ulu-0.009
J-0.008
ora-0.008
emo-0.008
Token cool
Token ID3608
Feature activation+3.27e+00

Pos logit contributions
J+0.030
ory+0.029
 common+0.028
ulu+0.028
 Jill+0.027
Neg logit contributions
zed-0.034
oved-0.033
opes-0.032
iously-0.031
 ow-0.031
Token water
Token ID1660
Feature activation+1.93e+00

Pos logit contributions
J+0.109
ulu+0.091
 common+0.091
Col+0.088
ory+0.087
Neg logit contributions
oved-0.109
iously-0.109
opes-0.107
zed-0.106
 ow-0.100
Token and
Token ID290
Feature activation+6.26e-01

Pos logit contributions
ulu+0.061
J+0.061
ory+0.058
 common+0.056
 Jill+0.053
Neg logit contributions
oved-0.068
zed-0.065
opes-0.065
iously-0.062
ths-0.061
Token started
Token ID2067
Feature activation+2.12e-02

Pos logit contributions
ulu+0.020
ory+0.020
J+0.020
 common+0.019
ola+0.018
Neg logit contributions
zed-0.021
oved-0.020
opes-0.019
ths-0.019
iously-0.019
Token playing
Token ID2712
Feature activation+1.93e-01

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token,
Token ID11
Feature activation-2.75e-02

Pos logit contributions
ory+0.007
ulu+0.006
J+0.006
 common+0.006
ola+0.006
Neg logit contributions
zed-0.006
oved-0.006
opes-0.006
ze-0.006
iously-0.005
Token loved
Token ID6151
Feature activation+4.04e-02

Pos logit contributions
oved+0.045
opes+0.044
iously+0.043
ths+0.041
zed+0.040
Neg logit contributions
ulu-0.065
J-0.064
ory-0.062
 common-0.059
ola-0.059
Token to
Token ID284
Feature activation+8.25e-01

Pos logit contributions
J+0.001
ulu+0.001
ory+0.001
 Jill+0.001
 Jenny+0.001
Neg logit contributions
oved-0.002
opes-0.002
zed-0.001
iously-0.001
ths-0.001
Token wear
Token ID5806
Feature activation+1.76e+00

Pos logit contributions
ulu+0.024
J+0.023
ory+0.023
 common+0.021
 Jill+0.020
Neg logit contributions
zed-0.031
oved-0.031
opes-0.029
erved-0.027
 ow-0.027
Token all
Token ID477
Feature activation-8.27e-01

Pos logit contributions
ulu+0.055
J+0.053
ory+0.053
 Jill+0.049
 common+0.048
Neg logit contributions
oved-0.064
zed-0.062
opes-0.061
ths-0.057
iously-0.057
Token the
Token ID262
Feature activation-7.83e-01

Pos logit contributions
oved+0.026
zed+0.025
opes+0.023
chair+0.022
 about+0.022
Neg logit contributions
ory-0.028
J-0.027
ulu-0.027
 common-0.025
Col-0.024
Token time
Token ID640
Feature activation+2.53e+00

Pos logit contributions
oved+0.027
opes+0.026
zed+0.025
 meanings+0.024
 ow+0.023
Neg logit contributions
ulu-0.025
ory-0.024
J-0.024
 Jill-0.023
ola-0.022
Token.
Token ID13
Feature activation+2.77e-03

Pos logit contributions
ulu+0.069
ory+0.066
J+0.066
 common+0.060
 Jill+0.059
Neg logit contributions
oved-0.102
zed-0.098
opes-0.097
ths-0.092
iously-0.091
Token One
Token ID1881
Feature activation+5.38e-01

Pos logit contributions
ulu+0.000
J+0.000
ory+0.000
 common+0.000
 Jill+0.000
Neg logit contributions
oved-0.000
zed-0.000
opes-0.000
ths-0.000
iously-0.000
Token day
Token ID1110
Feature activation-1.88e-01

Pos logit contributions
ulu+0.016
J+0.015
ory+0.015
 common+0.014
 Jill+0.014
Neg logit contributions
oved-0.021
zed-0.020
opes-0.019
ths-0.018
iously-0.018
Token,
Token ID11
Feature activation-4.81e-01

Pos logit contributions
oved+0.008
zed+0.007
opes+0.007
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 Jill-0.004
 common-0.004
Token Lily
Token ID20037
Feature activation+1.27e+00

Pos logit contributions
oved+0.023
zed+0.023
opes+0.022
ths+0.021
sed+0.021
Neg logit contributions
ulu-0.009
ory-0.009
J-0.008
 common-0.008
ora-0.007
Token to
Token ID284
Feature activation-1.19e-01

Pos logit contributions
ulu+0.041
J+0.040
ory+0.040
 common+0.037
 Jill+0.037
Neg logit contributions
oved-0.047
zed-0.045
opes-0.045
ths-0.042
iously-0.042
Token show
Token ID905
Feature activation+1.18e+00

Pos logit contributions
oved+0.004
zed+0.004
opes+0.004
 ow+0.003
ze+0.003
Neg logit contributions
J-0.004
ory-0.004
ulu-0.004
Col-0.003
ora-0.003
Token me
Token ID502
Feature activation+2.06e-01

Pos logit contributions
ulu+0.037
J+0.036
ory+0.035
 common+0.032
 Jill+0.031
Neg logit contributions
oved-0.042
opes-0.041
zed-0.041
ths-0.038
iously-0.037
Token?"
Token ID1701
Feature activation+6.68e-01

Pos logit contributions
J+0.006
ulu+0.006
ory+0.006
 common+0.005
 Jill+0.005
Neg logit contributions
oved-0.008
zed-0.007
opes-0.007
ths-0.007
iously-0.007
Token The
Token ID383
Feature activation+9.54e-01

Pos logit contributions
ulu+0.022
ory+0.022
J+0.022
 common+0.020
 Jill+0.020
Neg logit contributions
oved-0.022
zed-0.022
opes-0.021
iously-0.020
ths-0.020
Token butterfly
Token ID35113
Feature activation+6.92e-01

Pos logit contributions
ulu+0.027
ory+0.027
J+0.026
 common+0.024
 Jill+0.024
Neg logit contributions
oved-0.036
opes-0.035
zed-0.035
ths-0.034
sed-0.033
Token said
Token ID531
Feature activation+4.24e-01

Pos logit contributions
ulu+0.018
J+0.018
ory+0.017
 common+0.016
 Jill+0.016
Neg logit contributions
oved-0.028
zed-0.027
opes-0.027
ths-0.026
iously-0.026
Token,
Token ID11
Feature activation-3.28e-01

Pos logit contributions
ulu+0.012
J+0.012
ory+0.012
 common+0.011
 Jill+0.011
Neg logit contributions
oved-0.016
zed-0.016
opes-0.016
ths-0.015
iously-0.015
Token "
Token ID366
Feature activation-1.10e+00

Pos logit contributions
oved+0.012
opes+0.011
zed+0.011
erved+0.011
ths+0.010
Neg logit contributions
J-0.010
ulu-0.010
ory-0.010
 Jill-0.010
 mer-0.009
TokenFollow
Token ID7155
Feature activation+1.45e+00

Pos logit contributions
oved+0.037
zed+0.035
opes+0.035
ths+0.033
 meanings+0.032
Neg logit contributions
ory-0.035
ulu-0.035
 Jill-0.033
J-0.033
 common-0.031
Token me
Token ID502
Feature activation+5.69e-01

Pos logit contributions
ulu+0.052
ory+0.050
J+0.050
ola+0.045
 common+0.044
Neg logit contributions
opes-0.043
zed-0.041
oved-0.041
iously-0.040
ths-0.039
Token He
Token ID679
Feature activation-2.08e-01

Pos logit contributions
oved+0.002
zed+0.002
opes+0.002
sed+0.002
erved+0.002
Neg logit contributions
ulu-0.003
ory-0.003
J-0.003
ora-0.002
ola-0.002
Token picked
Token ID6497
Feature activation+5.24e-01

Pos logit contributions
oved+0.008
zed+0.007
opes+0.007
ths+0.007
iously+0.007
Neg logit contributions
ulu-0.006
J-0.006
ory-0.006
 common-0.006
 Jill-0.006
Token up
Token ID510
Feature activation-5.27e-01

Pos logit contributions
ulu+0.024
J+0.023
 common+0.022
ory+0.022
ola+0.020
Neg logit contributions
oved-0.011
zed-0.011
erved-0.010
iously-0.009
opes-0.009
Token his
Token ID465
Feature activation+3.02e-02

Pos logit contributions
zed+0.013
oved+0.013
erved+0.013
opes+0.012
 ow+0.012
Neg logit contributions
ulu-0.020
ory-0.019
ora-0.018
ola-0.018
Ar-0.018
Token fork
Token ID15563
Feature activation-1.11e+00

Pos logit contributions
ulu+0.001
J+0.001
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
iously-0.001
sed-0.001
Token and
Token ID290
Feature activation+8.98e-01

Pos logit contributions
oved+0.040
zed+0.037
opes+0.037
iously+0.036
ths+0.035
Neg logit contributions
ulu-0.036
J-0.035
ory-0.034
 common-0.033
 Jill-0.031
Token took
Token ID1718
Feature activation-2.60e-01

Pos logit contributions
ulu+0.029
ory+0.027
J+0.027
ola+0.025
 common+0.025
Neg logit contributions
zed-0.033
oved-0.031
opes-0.031
sed-0.029
ths-0.029
Token a
Token ID257
Feature activation+9.39e-01

Pos logit contributions
zed+0.008
oved+0.007
erved+0.007
ze+0.007
aged+0.007
Neg logit contributions
ulu-0.010
ory-0.010
ora-0.009
J-0.009
 common-0.008
Token small
Token ID1402
Feature activation+1.04e+00

Pos logit contributions
ulu+0.028
J+0.028
rust+0.027
ory+0.027
 Jill+0.026
Neg logit contributions
zed-0.031
chair-0.029
oved-0.029
 ow-0.028
zing-0.027
Token bite
Token ID13197
Feature activation+8.91e-01

Pos logit contributions
ulu+0.035
J+0.033
ory+0.031
 Jill+0.030
ola+0.030
Neg logit contributions
oved-0.035
zed-0.031
chair-0.031
sed-0.031
ze-0.030
Token of
Token ID286
Feature activation+1.92e-01

Pos logit contributions
ulu+0.032
ory+0.031
 common+0.031
J+0.031
Col+0.028
Neg logit contributions
oved-0.027
der-0.024
zed-0.024
iously-0.022
chair-0.022
Token girl
Token ID2576
Feature activation+1.24e+00

Pos logit contributions
J+0.051
ulu+0.050
ory+0.046
 common+0.046
ola+0.044
Neg logit contributions
oved-0.072
sed-0.070
ths-0.070
chair-0.069
 ow-0.067
Token found
Token ID1043
Feature activation+1.70e-01

Pos logit contributions
ulu+0.037
ory+0.036
J+0.035
 common+0.034
 Jill+0.032
Neg logit contributions
oved-0.046
zed-0.044
opes-0.043
ths-0.041
iously-0.040
Token the
Token ID262
Feature activation+1.39e-02

Pos logit contributions
ory+0.005
ulu+0.005
J+0.005
 common+0.005
ola+0.004
Neg logit contributions
oved-0.006
zed-0.006
opes-0.006
iously-0.006
ths-0.006
Token tough
Token ID5802
Feature activation-4.27e-01

Pos logit contributions
ulu+0.000
J+0.000
ory+0.000
 common+0.000
 Jill+0.000
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token magnet
Token ID19972
Feature activation+2.83e-01

Pos logit contributions
oved+0.016
opes+0.016
zed+0.015
iously+0.015
ths+0.014
Neg logit contributions
ulu-0.013
J-0.012
ory-0.012
 common-0.011
ola-0.011
Token.
Token ID13
Feature activation+5.27e-01

Pos logit contributions
ulu+0.006
ory+0.006
J+0.006
 Jill+0.006
ola+0.005
Neg logit contributions
zed-0.012
oved-0.012
opes-0.012
ths-0.011
erved-0.011
Token "
Token ID366
Feature activation-1.40e+00

Pos logit contributions
 Jill+0.015
J+0.014
ory+0.014
ulu+0.014
 Jenny+0.014
Neg logit contributions
oved-0.020
zed-0.020
opes-0.020
ths-0.019
sed-0.018
TokenHello
Token ID15496
Feature activation+1.94e+00

Pos logit contributions
oved+0.041
ths+0.037
zed+0.037
opes+0.035
ending+0.033
Neg logit contributions
ulu-0.053
ory-0.051
 common-0.048
 Jill-0.047
ola-0.047
Token,"
Token ID553
Feature activation+7.91e-01

Pos logit contributions
ulu+0.052
ory+0.051
J+0.050
 Jill+0.046
 common+0.046
Neg logit contributions
oved-0.078
zed-0.076
opes-0.075
iously-0.070
ths-0.070
Token she
Token ID673
Feature activation+3.51e-01

Pos logit contributions
ulu+0.023
ory+0.022
J+0.022
 common+0.020
ola+0.019
Neg logit contributions
oved-0.029
zed-0.029
opes-0.028
ths-0.028
iously-0.027
Token said
Token ID531
Feature activation+5.36e-01

Pos logit contributions
ulu+0.010
ory+0.010
J+0.010
 common+0.009
ola+0.009
Neg logit contributions
oved-0.013
zed-0.012
opes-0.012
iously-0.012
sed-0.012
Token.
Token ID13
Feature activation-3.15e-01

Pos logit contributions
ulu+0.053
J+0.051
ory+0.051
 Jill+0.046
 common+0.046
Neg logit contributions
oved-0.086
zed-0.083
opes-0.082
ths-0.078
iously-0.078
Token They
Token ID1119
Feature activation-2.65e-01

Pos logit contributions
oved+0.012
zed+0.012
opes+0.011
ths+0.011
iously+0.011
Neg logit contributions
ulu-0.009
ory-0.009
J-0.009
 common-0.008
 Jill-0.008
Token hope
Token ID2911
Feature activation-7.53e-01

Pos logit contributions
oved+0.011
zed+0.011
opes+0.011
ths+0.010
iously+0.010
Neg logit contributions
ulu-0.007
J-0.007
ory-0.006
 Jill-0.006
 common-0.006
Token the
Token ID262
Feature activation-3.83e-01

Pos logit contributions
oved+0.032
zed+0.031
opes+0.030
ths+0.029
iously+0.029
Neg logit contributions
ulu-0.019
ory-0.018
J-0.018
 common-0.016
 Jill-0.016
Token mosquito
Token ID35446
Feature activation-1.45e+00

Pos logit contributions
oved+0.013
opes+0.012
zed+0.012
iously+0.012
ths+0.011
Neg logit contributions
ulu-0.014
J-0.013
ory-0.012
 common-0.012
 Jill-0.012
Token does
Token ID857
Feature activation+8.88e-01

Pos logit contributions
oved+0.059
opes+0.057
zed+0.056
iously+0.054
ths+0.054
Neg logit contributions
ulu-0.037
ory-0.035
J-0.035
 common-0.033
 Jill-0.031
Token not
Token ID407
Feature activation+2.62e-01

Pos logit contributions
ulu+0.038
ory+0.038
J+0.036
ola+0.035
 Jill+0.034
Neg logit contributions
zed-0.023
oved-0.022
opes-0.020
erved-0.019
ths-0.019
Token come
Token ID1282
Feature activation+4.27e-02

Pos logit contributions
J+0.009
ulu+0.009
ory+0.009
ola+0.009
Col+0.008
Neg logit contributions
oved-0.007
 ow-0.007
ze-0.007
opes-0.007
zed-0.007
Token back
Token ID736
Feature activation-1.21e-01

Pos logit contributions
ulu+0.002
J+0.001
ory+0.001
ola+0.001
 common+0.001
Neg logit contributions
oved-0.001
opes-0.001
zed-0.001
erved-0.001
iously-0.001
Token.
Token ID13
Feature activation-2.97e-01

Pos logit contributions
oved+0.005
zed+0.005
opes+0.005
ths+0.004
iously+0.004
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 common-0.003
 Jill-0.003
Token<|endoftext|>
Token ID50256
Feature activation+3.26e-01

Pos logit contributions
oved+0.010
zed+0.010
opes+0.010
sed+0.009
erved+0.009
Neg logit contributions
ulu-0.010
ory-0.009
J-0.009
ola-0.008
 common-0.008
Token sauce
Token ID10746
Feature activation-2.16e+00

Pos logit contributions
oved+0.044
zed+0.043
opes+0.042
ths+0.041
iously+0.040
Neg logit contributions
ory-0.030
ulu-0.030
J-0.029
 common-0.028
 Jill-0.027
Token was
Token ID373
Feature activation-3.82e-01

Pos logit contributions
oved+0.081
zed+0.079
opes+0.078
ths+0.074
iously+0.073
Neg logit contributions
ulu-0.063
J-0.061
ory-0.061
 Jill-0.056
 common-0.056
Token better
Token ID1365
Feature activation+1.55e+00

Pos logit contributions
oved+0.012
zed+0.012
opes+0.011
ths+0.011
iously+0.011
Neg logit contributions
ulu-0.014
J-0.013
ory-0.013
ora-0.012
ola-0.012
Token.
Token ID13
Feature activation-4.53e-01

Pos logit contributions
ulu+0.051
J+0.050
ory+0.049
 common+0.046
 Jill+0.046
Neg logit contributions
oved-0.053
zed-0.051
opes-0.051
ths-0.048
iously-0.047
Token They
Token ID1119
Feature activation-7.93e-02

Pos logit contributions
oved+0.016
zed+0.016
opes+0.015
iously+0.014
ths+0.014
Neg logit contributions
ulu-0.014
J-0.014
ory-0.014
 common-0.013
 Jill-0.012
Token both
Token ID1111
Feature activation+1.03e-01

Pos logit contributions
oved+0.003
zed+0.003
opes+0.002
ths+0.002
iously+0.002
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 common-0.002
 Jill-0.002
Token felt
Token ID2936
Feature activation-6.59e-01

Pos logit contributions
ulu+0.003
J+0.003
ory+0.003
 common+0.003
 Jill+0.003
Neg logit contributions
oved-0.004
zed-0.004
opes-0.004
ths-0.003
iously-0.003
Token angry
Token ID7954
Feature activation-2.92e+00

Pos logit contributions
oved+0.023
zed+0.022
opes+0.021
ths+0.020
iously+0.020
Neg logit contributions
ulu-0.021
J-0.021
ory-0.020
 common-0.019
ola-0.018
Token and
Token ID290
Feature activation-3.57e-01

Pos logit contributions
zed+0.125
oved+0.123
opes+0.120
ths+0.114
sed+0.112
Neg logit contributions
ory-0.067
J-0.067
ulu-0.067
 Jill-0.066
 Jenny-0.061
Token sad
Token ID6507
Feature activation-7.41e-01

Pos logit contributions
oved+0.012
zed+0.011
opes+0.011
ths+0.011
iously+0.011
Neg logit contributions
ulu-0.012
J-0.012
ory-0.012
 common-0.011
 Jill-0.011
Token.
Token ID13
Feature activation-4.33e-01

Pos logit contributions
oved+0.032
zed+0.031
opes+0.031
ths+0.029
erved+0.029
Neg logit contributions
ory-0.016
ulu-0.016
 Jill-0.016
J-0.016
 Jenny-0.015
Token problem
Token ID1917
Feature activation-3.96e-01

Pos logit contributions
oved+0.052
zed+0.050
opes+0.049
iously+0.047
ths+0.047
Neg logit contributions
ulu-0.048
J-0.047
ory-0.046
 common-0.042
 Jill-0.042
Token,
Token ID11
Feature activation-1.24e+00

Pos logit contributions
oved+0.016
zed+0.015
opes+0.015
ths+0.014
iously+0.014
Neg logit contributions
ulu-0.011
ory-0.010
J-0.010
 Jill-0.010
 common-0.009
Token just
Token ID655
Feature activation+7.50e-01

Pos logit contributions
zed+0.043
oved+0.043
opes+0.041
ths+0.040
iously+0.040
Neg logit contributions
ulu-0.039
J-0.039
ory-0.037
 common-0.035
ora-0.033
Token be
Token ID307
Feature activation+1.19e+00

Pos logit contributions
ulu+0.022
J+0.022
ory+0.022
 common+0.019
 Jill+0.019
Neg logit contributions
oved-0.028
zed-0.027
opes-0.026
iously-0.025
ths-0.025
Token careful
Token ID8161
Feature activation-1.86e-01

Pos logit contributions
ory+0.045
ulu+0.044
J+0.042
 common+0.039
ora+0.039
Neg logit contributions
zed-0.035
oved-0.035
ths-0.032
opes-0.031
ze-0.030
Token and
Token ID290
Feature activation-1.42e-01

Pos logit contributions
oved+0.007
zed+0.007
opes+0.007
ths+0.007
sed+0.007
Neg logit contributions
ulu-0.005
ory-0.005
J-0.005
 Jill-0.005
 common-0.004
Token take
Token ID1011
Feature activation-2.89e-01

Pos logit contributions
oved+0.005
zed+0.005
opes+0.005
ths+0.005
iously+0.005
Neg logit contributions
ulu-0.004
ory-0.004
J-0.004
 common-0.004
 Jill-0.004
Token it
Token ID340
Feature activation-1.67e+00

Pos logit contributions
zed+0.011
oved+0.011
opes+0.010
iously+0.010
ths+0.010
Neg logit contributions
ulu-0.009
J-0.008
ory-0.008
 Jill-0.007
ola-0.007
Token easy
Token ID2562
Feature activation-5.11e-01

Pos logit contributions
oved+0.062
zed+0.060
opes+0.058
iously+0.055
ths+0.055
Neg logit contributions
ulu-0.050
J-0.049
ory-0.048
 common-0.045
 Jill-0.044
Token!"
Token ID2474
Feature activation+5.89e-01

Pos logit contributions
oved+0.019
zed+0.018
opes+0.018
ths+0.017
sed+0.017
Neg logit contributions
ulu-0.015
ory-0.015
J-0.015
 common-0.014
 Jill-0.013
Token
Token ID220
Feature activation-1.59e+00

Pos logit contributions
ulu+0.015
ory+0.015
J+0.015
 common+0.014
 Jill+0.013
Neg logit contributions
oved-0.024
zed-0.024
opes-0.023
iously-0.022
ths-0.022
Token their
Token ID511
Feature activation-7.90e-01

Pos logit contributions
ory+0.007
ulu+0.007
J+0.007
 common+0.006
ola+0.006
Neg logit contributions
oved-0.006
zed-0.006
opes-0.006
ths-0.005
iously-0.005
Token k
Token ID479
Feature activation-4.82e-01

Pos logit contributions
zed+0.033
oved+0.032
opes+0.030
iously+0.030
der+0.028
Neg logit contributions
ulu-0.019
 common-0.019
ory-0.019
oe-0.018
J-0.017
Tokenites
Token ID2737
Feature activation-7.20e-01

Pos logit contributions
oved+0.018
zed+0.018
opes+0.017
iously+0.016
ths+0.016
Neg logit contributions
ulu-0.014
J-0.014
ory-0.014
 common-0.013
 Jill-0.013
Token and
Token ID290
Feature activation+5.00e-02

Pos logit contributions
oved+0.027
zed+0.027
opes+0.027
iously+0.025
ths+0.025
Neg logit contributions
ulu-0.020
J-0.019
ory-0.019
 Jill-0.018
 common-0.018
Token their
Token ID511
Feature activation-6.40e-01

Pos logit contributions
ulu+0.002
ory+0.002
J+0.002
ola+0.001
 common+0.001
Neg logit contributions
zed-0.002
oved-0.002
opes-0.002
sed-0.002
ths-0.002
Token dolls
Token ID36062
Feature activation-8.10e-01

Pos logit contributions
zed+0.026
oved+0.025
iously+0.024
opes+0.023
ending+0.023
Neg logit contributions
 common-0.016
ulu-0.015
ory-0.015
J-0.014
 water-0.014
Token.
Token ID13
Feature activation-2.63e-01

Pos logit contributions
opes+0.037
oved+0.036
ths+0.036
zed+0.036
iously+0.035
Neg logit contributions
ulu-0.016
J-0.015
ory-0.014
 Jill-0.013
 common-0.013
Token They
Token ID1119
Feature activation-3.46e-01

Pos logit contributions
oved+0.010
zed+0.010
opes+0.010
ths+0.009
iously+0.009
Neg logit contributions
ulu-0.008
ory-0.007
J-0.007
 common-0.007
 Jill-0.007
Token had
Token ID550
Feature activation-6.10e-01

Pos logit contributions
oved+0.012
zed+0.012
opes+0.011
sed+0.010
ths+0.010
Neg logit contributions
ory-0.011
ulu-0.011
J-0.011
 common-0.010
 Jill-0.010
Token fun
Token ID1257
Feature activation+1.36e+00

Pos logit contributions
oved+0.027
zed+0.026
opes+0.026
ths+0.025
iously+0.025
Neg logit contributions
J-0.014
ulu-0.014
ory-0.013
 Jill-0.013
 common-0.013
Token in
Token ID287
Feature activation-3.40e-01

Pos logit contributions
J+0.022
ulu+0.021
 mer+0.020
 common+0.019
 Jill+0.018
Neg logit contributions
erved-0.066
zed-0.065
oved-0.065
iously-0.064
opes-0.064
Token."
Token ID526
Feature activation+1.35e+00

Pos logit contributions
ory+0.013
ulu+0.013
J+0.013
 common+0.012
 Jill+0.011
Neg logit contributions
zed-0.026
oved-0.026
opes-0.025
ths-0.024
iously-0.024
Token<|endoftext|>
Token ID50256
Feature activation+2.14e-01

Pos logit contributions
ulu+0.045
ory+0.042
J+0.041
 common+0.039
ola+0.038
Neg logit contributions
oved-0.046
opes-0.043
zed-0.043
sed-0.040
erved-0.040
TokenL
Token ID43
Feature activation+1.20e+00

Pos logit contributions
ory+0.008
ulu+0.008
 common+0.007
J+0.007
 Jill+0.007
Neg logit contributions
oved-0.006
zed-0.006
opes-0.006
 Leave-0.005
chair-0.005
Tokenily
Token ID813
Feature activation+6.50e-01

Pos logit contributions
 common+0.032
 mer+0.031
ulu+0.030
 mineral+0.030
ory+0.029
Neg logit contributions
oved-0.046
opes-0.043
zed-0.043
erved-0.040
iously-0.040
Token did
Token ID750
Feature activation-9.07e-02

Pos logit contributions
ulu+0.018
ory+0.017
J+0.017
 Jill+0.016
 common+0.015
Neg logit contributions
oved-0.026
zed-0.025
opes-0.025
ths-0.024
iously-0.024
Token not
Token ID407
Feature activation-1.31e-01

Pos logit contributions
oved+0.004
opes+0.004
ths+0.004
zed+0.004
iously+0.004
Neg logit contributions
J-0.002
ulu-0.002
ory-0.002
 Jill-0.002
 common-0.002
Token like
Token ID588
Feature activation+3.21e-01

Pos logit contributions
oved+0.005
zed+0.005
opes+0.004
erved+0.004
ths+0.004
Neg logit contributions
ulu-0.004
ory-0.004
J-0.004
ola-0.003
ora-0.003
Token school
Token ID1524
Feature activation-3.90e-01

Pos logit contributions
ulu+0.011
J+0.011
ory+0.011
 Jill+0.010
 common+0.010
Neg logit contributions
oved-0.010
zed-0.010
opes-0.010
ths-0.009
iously-0.009
Token.
Token ID13
Feature activation-2.51e-02

Pos logit contributions
zed+0.017
opes+0.017
oved+0.017
iously+0.016
sed+0.016
Neg logit contributions
J-0.009
ulu-0.009
ory-0.009
 Jill-0.008
 common-0.008
Token She
Token ID1375
Feature activation-9.86e-01

Pos logit contributions
oved+0.001
opes+0.000
zed+0.000
 meanings+0.000
iously+0.000
Neg logit contributions
ulu-0.001
ory-0.001
J-0.001
 common-0.001
 mer-0.001
Token thought
Token ID1807
Feature activation-1.85e+00

Pos logit contributions
oved+0.033
zed+0.031
opes+0.031
ths+0.029
iously+0.029
Neg logit contributions
ulu-0.034
ory-0.033
J-0.033
 common-0.030
 Jill-0.030
Token to
Token ID284
Feature activation-1.51e-01

Pos logit contributions
ory+0.060
ulu+0.060
 Jill+0.059
J+0.058
 Jenny+0.057
Neg logit contributions
oved-0.075
zed-0.074
opes-0.072
ths-0.069
iously-0.066
Token pack
Token ID2353
Feature activation+2.17e-01

Pos logit contributions
zed+0.005
oved+0.005
ze+0.005
opes+0.005
zy+0.004
Neg logit contributions
ory-0.005
J-0.005
ulu-0.005
ora-0.004
 common-0.004
Token your
Token ID534
Feature activation+3.41e-01

Pos logit contributions
ulu+0.007
J+0.007
ory+0.007
 common+0.006
ora+0.006
Neg logit contributions
oved-0.007
zed-0.007
opes-0.007
iously-0.007
ths-0.007
Token backpack
Token ID22526
Feature activation-1.57e+00

Pos logit contributions
ulu+0.009
ory+0.009
J+0.009
 common+0.008
 Jill+0.008
Neg logit contributions
oved-0.013
zed-0.013
opes-0.013
ths-0.012
iously-0.012
Token for
Token ID329
Feature activation-1.97e+00

Pos logit contributions
oved+0.062
zed+0.061
opes+0.060
ths+0.057
iously+0.056
Neg logit contributions
ulu-0.043
ory-0.042
J-0.042
 Jill-0.039
 common-0.038
Token school
Token ID1524
Feature activation-4.31e-03

Pos logit contributions
oved+0.079
zed+0.076
opes+0.076
ths+0.072
iously+0.071
Neg logit contributions
ulu-0.053
J-0.051
ory-0.051
 common-0.047
 Jill-0.046
Token tomorrow
Token ID9439
Feature activation-9.77e-02

Pos logit contributions
oved+0.000
zed+0.000
opes+0.000
ths+0.000
iously+0.000
Neg logit contributions
ulu-0.000
ory-0.000
J-0.000
 common-0.000
 Jill-0.000
Token,"
Token ID553
Feature activation-2.60e-01

Pos logit contributions
oved+0.004
zed+0.004
opes+0.004
ths+0.003
iously+0.003
Neg logit contributions
ulu-0.003
ory-0.003
J-0.003
 common-0.002
 Jill-0.002
Token her
Token ID607
Feature activation-2.58e-01

Pos logit contributions
oved+0.011
opes+0.011
zed+0.011
iously+0.010
ths+0.010
Neg logit contributions
ulu-0.006
J-0.006
ory-0.006
 Jill-0.006
 common-0.005
Token mom
Token ID1995
Feature activation-2.88e-01

Pos logit contributions
oved+0.011
zed+0.011
opes+0.011
iously+0.011
ths+0.010
Neg logit contributions
ulu-0.006
J-0.006
ory-0.006
 Jill-0.005
 common-0.005
Token said
Token ID531
Feature activation+6.06e-01

Pos logit contributions
oved+0.013
zed+0.012
opes+0.012
ths+0.012
iously+0.012
Neg logit contributions
ulu-0.007
J-0.006
ory-0.006
 Jill-0.006
 common-0.006
Token He
Token ID679
Feature activation+1.08e+00

Pos logit contributions
ulu+0.038
ory+0.036
J+0.034
 common+0.034
ora+0.033
Neg logit contributions
oved-0.028
zed-0.026
der-0.025
opes-0.025
sed-0.024
Token said
Token ID531
Feature activation+8.58e-01

Pos logit contributions
ulu+0.028
ory+0.027
J+0.027
 common+0.025
 Jill+0.024
Neg logit contributions
oved-0.044
zed-0.042
opes-0.042
ths-0.040
sed-0.040
Token,
Token ID11
Feature activation+7.21e-02

Pos logit contributions
ulu+0.026
J+0.025
ory+0.025
 common+0.023
 Jill+0.022
Neg logit contributions
oved-0.032
zed-0.031
opes-0.030
iously-0.028
ths-0.028
Token "
Token ID366
Feature activation-9.95e-01

Pos logit contributions
ulu+0.002
J+0.002
ory+0.002
 Jill+0.002
 common+0.002
Neg logit contributions
oved-0.002
opes-0.002
zed-0.002
ths-0.002
iously-0.002
TokenMy
Token ID3666
Feature activation+5.13e-01

Pos logit contributions
oved+0.033
zed+0.031
opes+0.031
ths+0.029
iously+0.028
Neg logit contributions
ulu-0.034
ory-0.034
J-0.031
 Jill-0.031
 common-0.030
Token shadow
Token ID9082
Feature activation-3.00e+00

Pos logit contributions
ulu+0.016
J+0.016
ory+0.016
 common+0.015
 Jill+0.015
Neg logit contributions
oved-0.018
zed-0.017
opes-0.017
ths-0.016
iously-0.016
Token is
Token ID318
Feature activation+1.10e+00

Pos logit contributions
oved+0.111
zed+0.108
opes+0.105
ths+0.101
iously+0.100
Neg logit contributions
ulu-0.089
ory-0.085
J-0.084
 common-0.080
 Jill-0.080
Token different
Token ID1180
Feature activation+1.01e+00

Pos logit contributions
ory+0.039
ulu+0.038
J+0.038
ora+0.034
ola+0.034
Neg logit contributions
oved-0.035
opes-0.033
zed-0.033
sed-0.031
ths-0.030
Token because
Token ID780
Feature activation-2.58e-01

Pos logit contributions
ulu+0.030
J+0.029
ory+0.029
 common+0.026
 Jill+0.026
Neg logit contributions
oved-0.039
opes-0.037
zed-0.037
iously-0.035
ths-0.034
Token I
Token ID314
Feature activation+1.55e+00

Pos logit contributions
oved+0.010
zed+0.010
opes+0.010
ths+0.009
iously+0.009
Neg logit contributions
ory-0.007
ulu-0.007
J-0.007
 common-0.006
ora-0.006
Token have
Token ID423
Feature activation+1.01e+00

Pos logit contributions
J+0.050
ulu+0.050
ory+0.048
 Jill+0.044
ola+0.043
Neg logit contributions
oved-0.052
zed-0.049
opes-0.048
sed-0.046
 meanings-0.044
Token for
Token ID329
Feature activation-2.09e+00

Pos logit contributions
oved+0.046
opes+0.044
zed+0.043
sed+0.042
ths+0.041
Neg logit contributions
ulu-0.035
J-0.035
ory-0.033
 common-0.031
 Jill-0.030
Token Emma
Token ID18966
Feature activation+8.69e-02

Pos logit contributions
zed+0.072
oved+0.071
opes+0.071
ths+0.065
iously+0.065
Neg logit contributions
ulu-0.066
J-0.062
ory-0.062
 common-0.059
ora-0.058
Token and
Token ID290
Feature activation+1.66e-01

Pos logit contributions
ulu+0.003
J+0.003
ory+0.003
 common+0.002
 Jill+0.002
Neg logit contributions
oved-0.003
zed-0.003
opes-0.003
iously-0.003
ths-0.003
Token her
Token ID607
Feature activation-1.19e+00

Pos logit contributions
ulu+0.005
J+0.005
ory+0.004
 common+0.004
ola+0.004
Neg logit contributions
zed-0.006
oved-0.006
opes-0.006
ths-0.006
iously-0.006
Token little
Token ID1310
Feature activation-1.77e-01

Pos logit contributions
oved+0.044
zed+0.043
opes+0.042
ths+0.040
iously+0.040
Neg logit contributions
ulu-0.036
ory-0.035
J-0.035
 Jill-0.032
 common-0.032
Token brother
Token ID3956
Feature activation-2.86e+00

Pos logit contributions
oved+0.007
opes+0.006
zed+0.006
sed+0.006
iously+0.006
Neg logit contributions
ulu-0.005
J-0.005
ory-0.005
 common-0.005
ola-0.004
Token Tom
Token ID4186
Feature activation+7.12e-03

Pos logit contributions
oved+0.102
zed+0.097
opes+0.093
iously+0.088
ths+0.086
Neg logit contributions
ulu-0.091
J-0.083
ory-0.081
 common-0.081
ola-0.075
Token.
Token ID13
Feature activation-1.37e-01

Pos logit contributions
ulu+0.000
J+0.000
ory+0.000
 common+0.000
ora+0.000
Neg logit contributions
oved-0.000
zed-0.000
opes-0.000
iously-0.000
aged-0.000
Token Tom
Token ID4186
Feature activation+1.37e+00

Pos logit contributions
oved+0.005
opes+0.005
zed+0.005
sed+0.004
iously+0.004
Neg logit contributions
ulu-0.004
J-0.004
ory-0.004
 common-0.004
ola-0.004
Token grabbed
Token ID13176
Feature activation-9.58e-02

Pos logit contributions
ulu+0.050
J+0.048
ory+0.047
 common+0.044
 Jill+0.043
Neg logit contributions
oved-0.043
opes-0.041
zed-0.041
sed-0.038
ths-0.037
Token the
Token ID262
Feature activation+2.99e-01

Pos logit contributions
opes+0.003
oved+0.003
zed+0.003
 ow+0.003
sed+0.003
Neg logit contributions
ulu-0.003
ory-0.003
J-0.003
ora-0.003
 common-0.003
Token,
Token ID11
Feature activation-4.69e-01

Pos logit contributions
zed+0.004
oved+0.004
opes+0.003
ths+0.003
iously+0.003
Neg logit contributions
ulu-0.003
J-0.003
ory-0.003
 common-0.003
rust-0.003
Token hopefully
Token ID11481
Feature activation+2.45e-01

Pos logit contributions
zed+0.016
oved+0.016
opes+0.016
ths+0.015
iously+0.015
Neg logit contributions
ulu-0.014
J-0.014
ory-0.014
 common-0.013
 Jill-0.012
Token you
Token ID345
Feature activation+1.54e+00

Pos logit contributions
ulu+0.008
J+0.007
ory+0.007
 common+0.006
ola+0.006
Neg logit contributions
oved-0.009
zed-0.009
opes-0.008
iously-0.008
ths-0.008
Tokenâ
Token ID22940
Feature activation+3.71e-02

Pos logit contributions
J+0.048
ulu+0.046
ory+0.044
 Jill+0.042
 common+0.041
Neg logit contributions
oved-0.055
zed-0.052
opes-0.051
iously-0.048
ths-0.048
Token
Token ID26391
Feature activation-1.50e+00

Pos logit contributions
ulu+0.001
ory+0.001
J+0.001
 common+0.001
 Jill+0.001
Neg logit contributions
oved-0.001
zed-0.001
opes-0.001
ths-0.001
iously-0.001
Token
Token ID8151
Feature activation-4.13e+00

Pos logit contributions
oved+0.047
opes+0.044
zed+0.043
iously+0.043
der+0.040
Neg logit contributions
J-0.054
ory-0.051
ulu-0.051
 Jill-0.051
 Jenny-0.049
Tokenll
Token ID297
Feature activation+1.16e-01

Pos logit contributions
oved+0.166
zed+0.158
opes+0.154
iously+0.147
ths+0.145
Neg logit contributions
ulu-0.107
ory-0.105
J-0.105
 common-0.102
 Jill-0.094
Token see
Token ID766
Feature activation-1.60e-02

Pos logit contributions
J+0.003
ulu+0.003
ory+0.003
 common+0.003
 Jill+0.003
Neg logit contributions
oved-0.004
zed-0.004
opes-0.004
iously-0.004
erved-0.004
Token a
Token ID257
Feature activation+5.71e-01

Pos logit contributions
oved+0.001
zed+0.001
opes+0.001
ths+0.001
iously+0.001
Neg logit contributions
ulu-0.000
J-0.000
ory-0.000
 Jill-0.000
 common-0.000
Token purple
Token ID14032
Feature activation+2.18e-01

Pos logit contributions
ulu+0.020
J+0.019
ory+0.018
ola+0.017
 Jill+0.017
Neg logit contributions
oved-0.017
ths-0.017
zed-0.017
 ow-0.016
sed-0.016
Token sunset
Token ID26428
Feature activation+7.86e-02

Pos logit contributions
ulu+0.007
J+0.006
ory+0.006
 common+0.006
 Jill+0.006
Neg logit contributions
oved-0.008
zed-0.008
opes-0.008
iously-0.007
ths-0.007
Token took
Token ID1718
Feature activation-2.38e-01

Pos logit contributions
oved+0.047
opes+0.045
zed+0.045
iously+0.042
ths+0.042
Neg logit contributions
ulu-0.036
ory-0.035
J-0.035
 Jill-0.033
 common-0.032
Token his
Token ID465
Feature activation-7.77e-01

Pos logit contributions
zed+0.008
oved+0.008
opes+0.008
iously+0.008
ths+0.007
Neg logit contributions
ulu-0.008
ory-0.007
J-0.007
 common-0.007
ora-0.006
Token friend
Token ID1545
Feature activation-5.23e-01

Pos logit contributions
oved+0.030
zed+0.029
opes+0.028
ths+0.027
iously+0.026
Neg logit contributions
ulu-0.022
ory-0.021
J-0.021
 common-0.020
 Jill-0.020
Tokenâ
Token ID22940
Feature activation+3.37e-01

Pos logit contributions
oved+0.017
zed+0.017
opes+0.017
ths+0.016
iously+0.015
Neg logit contributions
ulu-0.017
ory-0.017
J-0.017
 Jill-0.016
 common-0.016
Token
Token ID26391
Feature activation-1.01e+00

Pos logit contributions
ulu+0.013
J+0.012
ory+0.012
 common+0.012
 Jill+0.012
Neg logit contributions
oved-0.010
zed-0.010
opes-0.009
iously-0.009
ths-0.009
Token
Token ID8151
Feature activation-3.54e+00

Pos logit contributions
oved+0.027
opes+0.026
zed+0.025
iously+0.024
ths+0.023
Neg logit contributions
J-0.041
ory-0.039
ulu-0.039
 Jill-0.038
 common-0.037
Tokens
Token ID82
Feature activation+1.99e-01

Pos logit contributions
oved+0.127
zed+0.120
opes+0.117
iously+0.111
ths+0.110
Neg logit contributions
ulu-0.111
J-0.107
ory-0.107
 common-0.102
 Jill-0.097
Token advice
Token ID5608
Feature activation+1.20e-01

Pos logit contributions
ulu+0.006
J+0.006
ory+0.006
 Jill+0.006
 common+0.006
Neg logit contributions
oved-0.007
zed-0.007
opes-0.007
ths-0.006
iously-0.006
Token.
Token ID13
Feature activation-1.47e-02

Pos logit contributions
ulu+0.003
J+0.003
ory+0.003
 common+0.003
 Jill+0.003
Neg logit contributions
oved-0.005
zed-0.005
opes-0.005
ths-0.004
iously-0.004
Token He
Token ID679
Feature activation-2.80e-01

Pos logit contributions
oved+0.000
zed+0.000
opes+0.000
iously+0.000
ths+0.000
Neg logit contributions
ulu-0.001
J-0.001
ory-0.001
 common-0.001
 mer-0.000
Token stayed
Token ID9658
Feature activation+8.09e-01

Pos logit contributions
oved+0.011
zed+0.011
opes+0.011
iously+0.010
ths+0.010
Neg logit contributions
ulu-0.008
ory-0.007
J-0.007
 common-0.007
 Jill-0.007
Token He
Token ID679
Feature activation-9.01e-01

Pos logit contributions
oved+0.027
zed+0.026
opes+0.026
iously+0.024
ths+0.024
Neg logit contributions
ulu-0.031
ory-0.029
J-0.029
 common-0.028
ora-0.026
Token knew
Token ID2993
Feature activation-2.23e+00

Pos logit contributions
oved+0.034
zed+0.033
opes+0.032
ths+0.030
iously+0.030
Neg logit contributions
ulu-0.027
J-0.026
ory-0.026
 Jill-0.024
 common-0.024
Token that
Token ID326
Feature activation+3.86e-01

Pos logit contributions
oved+0.070
zed+0.068
opes+0.066
ths+0.063
iously+0.062
Neg logit contributions
ulu-0.080
ory-0.078
J-0.077
 common-0.072
 Jill-0.071
Token all
Token ID477
Feature activation+6.70e-02

Pos logit contributions
ulu+0.011
ory+0.011
J+0.010
 common+0.009
ora+0.009
Neg logit contributions
oved-0.015
zed-0.015
opes-0.014
ths-0.014
iously-0.013
Token his
Token ID465
Feature activation-2.01e+00

Pos logit contributions
ulu+0.002
J+0.002
ory+0.001
 Jill+0.001
 common+0.001
Neg logit contributions
oved-0.003
zed-0.003
opes-0.003
iously-0.003
ths-0.003
Token hard
Token ID1327
Feature activation-2.69e+00

Pos logit contributions
oved+0.072
zed+0.069
opes+0.068
iously+0.064
ths+0.064
Neg logit contributions
ulu-0.061
ory-0.060
J-0.060
 common-0.058
 Jill-0.056
Token work
Token ID670
Feature activation-2.29e-01

Pos logit contributions
oved+0.108
zed+0.104
opes+0.103
ths+0.097
iously+0.097
Neg logit contributions
ulu-0.071
ory-0.070
J-0.069
 common-0.065
 Jill-0.064
Token,
Token ID11
Feature activation-6.46e-01

Pos logit contributions
oved+0.008
opes+0.008
zed+0.008
iously+0.008
ths+0.008
Neg logit contributions
ulu-0.007
J-0.007
ory-0.007
 common-0.006
 Jill-0.006
Token practice
Token ID3357
Feature activation+1.19e+00

Pos logit contributions
oved+0.024
zed+0.023
opes+0.023
ths+0.022
iously+0.022
Neg logit contributions
ulu-0.019
J-0.019
ory-0.019
 common-0.017
 Jill-0.017
Token and
Token ID290
Feature activation+1.49e-01

Pos logit contributions
ulu+0.036
J+0.035
ory+0.035
 common+0.033
 Jill+0.033
Neg logit contributions
oved-0.043
zed-0.041
opes-0.041
iously-0.039
ths-0.038
Token creativity
Token ID16389
Feature activation+2.82e-02

Pos logit contributions
ulu+0.005
ory+0.005
J+0.005
 common+0.004
 Jill+0.004
Neg logit contributions
oved-0.005
zed-0.005
opes-0.005
ths-0.005
iously-0.005